diff --git a/server/routers/chat_router.py b/server/routers/chat_router.py
index ad691346..b10945c4 100644
--- a/server/routers/chat_router.py
+++ b/server/routers/chat_router.py
@@ -171,32 +171,34 @@ def chat_agent(agent_name: str,
             **kwargs
         }, ensure_ascii=False).encode('utf-8') + b"\n"
 
-    try:
-        agent = agent_manager.get_runnable_agent(agent_name)
-    except Exception as e:
-        logger.error(f"Error getting agent {agent_name}: {e}")
-        return StreamingResponse(make_chunk(message=f"Error getting agent {agent_name}: {e}", status="error"), media_type='application/json')
 
-    # 从config中获取history_round
-    history_round = config.get("history_round")
-    history_manager = HistoryManager(history)
-    messages = history_manager.get_history_with_msg(query, max_rounds=history_round)
-    history_manager.add_user(query)
-
-    # 如果没有thread_id则生成一个
-    if "thread_id" not in config or not config["thread_id"]:
-        config["thread_id"] = str(uuid.uuid4())
-
-    # 构造运行时配置
-    runnable_config = {
-        "configurable": {
-            **config
-        }
-    }
 
     def stream_messages():
-        content = ""
+
+        # 代表服务端已经收到了请求
         yield make_chunk(status="init", meta=meta)
+
+        try:
+            agent = agent_manager.get_runnable_agent(agent_name)
+        except Exception as e:
+            logger.error(f"Error getting agent {agent_name}: {e}, {traceback.format_exc()}")
+            yield make_chunk(message=f"Error getting agent {agent_name}: {e}", status="error")
+            return
+
+        # 从config中获取history_round
+        history_round = config.get("history_round")
+        history_manager = HistoryManager(history)
+        messages = history_manager.get_history_with_msg(query, max_rounds=history_round)
+        history_manager.add_user(query)
+
+        # 构造运行时配置，如果没有thread_id则生成一个
+        if "thread_id" not in config or not config["thread_id"]:
+            config["thread_id"] = str(uuid.uuid4())
+
+        runnable_config = {"configurable": {**config}}
+
+        content = ""
+
         try:
             for msg, metadata in agent.stream_messages(messages, config_schema=runnable_config):
                 if isinstance(msg, AIMessageChunk) and msg.content != "<tool_call>":
@@ -214,7 +216,7 @@ def chat_agent(agent_name: str,
                             history=history_manager.update_ai(content),
                             meta=meta)
         except Exception as e:
-            logger.error(f"Error streaming messages: {e}")
+            logger.error(f"Error streaming messages: {e}, {traceback.format_exc()}")
             yield make_chunk(message=f"Error streaming messages: {e}", status="error")
 
     return StreamingResponse(stream_messages(), media_type='application/json')
diff --git a/src/agents/registry.py b/src/agents/registry.py
index dc974bd7..9ed7eca5 100644
--- a/src/agents/registry.py
+++ b/src/agents/registry.py
@@ -3,6 +3,7 @@ from __future__ import annotations
 import os
 
 from typing import Type, Annotated, Optional, TypedDict
+from enum import Enum
 from abc import abstractmethod
 from dataclasses import dataclass, fields, field
 
@@ -96,7 +97,7 @@ class BaseAgent():
             return
         for requirement in self.requirements:
             if requirement not in os.environ:
-                raise ValueError(f"{requirement} is not set")
+                raise ValueError(f"没有配置{requirement} 环境变量，请在 src/.env 文件中配置，并重新启动服务")
 
     def stream_values(self, messages: list[str], config_schema: RunnableConfig = None, **kwargs):
         graph = self.get_graph(config_schema=config_schema, **kwargs)
diff --git a/src/config/__init__.py b/src/config/__init__.py
index 5da6842c..da6bcac8 100644
--- a/src/config/__init__.py
+++ b/src/config/__init__.py
@@ -47,7 +47,7 @@ class Config(SimpleConfig):
         self.add_item("enable_reranker", default=False, des="是否开启重排序")
         self.add_item("enable_knowledge_base", default=False, des="是否开启知识库")
         self.add_item("enable_knowledge_graph", default=False, des="是否开启知识图谱")
-        self.add_item("enable_web_search", default=False, des="是否开启网页搜索（需配置 TAVILY_API_KEY）")
+        self.add_item("enable_web_search", default=False, des="是否开启网页搜索（注：现阶段会根据 TAVILY_API_KEY 自动开启，无法手动配置，将会在下个版本移除此配置项）")
         # 模型配置
         ## 注意这里是模型名，而不是具体的模型路径，默认使用 HuggingFace 的路径
         ## 如果需要自定义本地模型路径，则在 src/.env 中配置 MODEL_DIR
@@ -150,9 +150,13 @@ class Config(SimpleConfig):
             self.model_provider_status[provider] = all(conds_bool)
 
         # 检查web_search的环境变量
-        if self.enable_web_search and not os.getenv("TAVILY_API_KEY"):
-            logger.warning("TAVILY_API_KEY not set, web search will be disabled")
-            self.enable_web_search = False
+        # if self.enable_web_search and not os.getenv("TAVILY_API_KEY"):
+        #     logger.warning("TAVILY_API_KEY not set, web search will be disabled")
+        #     self.enable_web_search = False
+
+        # 2025.04.08 修改为不手动配置，只要配置了TAVILY_API_KEY，就默认开启web_search
+        if os.getenv("TAVILY_API_KEY"):
+            self.enable_web_search = True
 
         self.valuable_model_provider = [k for k, v in self.model_provider_status.items() if v]
         assert len(self.valuable_model_provider) > 0, f"No model provider available, please check your `.env` file. API_KEY_LIST: {conds}"
diff --git a/src/models/chat_model.py b/src/models/chat_model.py
index 065d9e36..0aacd6f6 100644
--- a/src/models/chat_model.py
+++ b/src/models/chat_model.py
@@ -1,18 +1,19 @@
 import os
+import requests
 from openai import OpenAI
 from src.utils import logger, get_docker_safe_url
 from langchain_openai import ChatOpenAI
 
 class OpenAIBase():
-    def __init__(self, api_key, base_url, model_name):
+    def __init__(self, api_key, base_url, model_name, **kwargs):
         self.api_key = api_key
         self.base_url = base_url
         self.client = OpenAI(api_key=api_key, base_url=base_url)
         self.model_name = model_name
+        self.info = kwargs
         self.chat_open_ai = ChatOpenAI(model=model_name,
                                        api_key=api_key,
-                                       base_url=base_url,
-                                       temperature=0.7)
+                                       base_url=base_url)
 
     def predict(self, message, stream=False):
         if isinstance(message, str):
@@ -54,6 +55,49 @@ class OpenAIBase():
             logger.error(f"Error getting models: {e}")
             return []
 
+    def _get_model_by_model_url(self, model_url):
+        """
+        Refs: https://docs.together.ai/reference/models-1
+
+        Return: [
+            {
+                "id": "meta-llama/Meta-Llama-3-70B-Instruct-Turbo",
+                "object": "model",
+                "created": 0,
+                "type": "chat",
+                "running": false,
+                "display_name": "Meta Llama 3 70B Instruct Turbo",
+                "organization": "Meta",
+                "link": "https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct",
+                "license": "Llama-3 (Other)",
+                "context_length": 8192,
+                "config": {
+                    "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}",
+                    "stop": [
+                        "<|eot_id|>"
+                    ],
+                    "bos_token": "<|begin_of_text|>",
+                    "eos_token": "<|end_of_text|>"
+                },
+                "pricing": {
+                    "hourly": 0,
+                    "input": 0.88,
+                    "output": 0.88,
+                    "base": 0,
+                    "finetune": 0
+                }
+            },
+        ]
+
+        """
+        headers = {
+            "accept": "application/json",
+            "authorization": f"Bearer {self.api_key}"
+        }
+        response = requests.get(model_url, headers=headers)
+        return response.json()
+
+
 
 class OpenModel(OpenAIBase):
     def __init__(self, model_name=None):
diff --git a/web/src/components/AgentChatComponent.vue b/web/src/components/AgentChatComponent.vue
index d1e072cc..5272d74b 100644
--- a/web/src/components/AgentChatComponent.vue
+++ b/web/src/components/AgentChatComponent.vue
@@ -511,6 +511,18 @@ const handleStreamResponse = async (response) => {
     }
   } catch (error) {
     console.error('流式处理出错:', error);
+    const lastMsg = messages.value[messages.value.length - 1];
+    if (lastMsg.role === 'assistant') {
+      lastMsg.status = 'error';
+      lastMsg.message = error.message;
+    } else {
+      messages.value.push({
+        role: 'assistant',
+        message: `发生错误: ${error.message}`,
+        status: 'error'
+      });
+      await scrollToBottom();
+    }
     isProcessing.value = false;
   }
 };
diff --git a/web/src/components/MessageComponent.vue b/web/src/components/MessageComponent.vue
index 1a5d0a88..09d1a088 100644
--- a/web/src/components/MessageComponent.vue
+++ b/web/src/components/MessageComponent.vue
@@ -48,7 +48,7 @@
         previewTheme="github"
         :showCodeRowNumber="false"
         :modelValue="message.content"
-        :key="index"
+        :key="message.id"
         class="message-md"/>
 
       <div v-if="message.isStoppedByUser" class="retry-hint">
diff --git a/web/src/views/SettingView.vue b/web/src/views/SettingView.vue
index 6af88d50..c8ba40df 100644
--- a/web/src/views/SettingView.vue
+++ b/web/src/views/SettingView.vue
@@ -6,7 +6,7 @@
       </template>
       <template #actions>
         <a-button :type="isNeedRestart ? 'primary' : 'default'" @click="sendRestart" :icon="h(ReloadOutlined)">
-          {{ isNeedRestart ? '需要重启' : '重启服务' }}
+          {{ isNeedRestart ? '需要刷新' : '重新加载' }}
         </a-button>
       </template>
     </HeaderComponent>
@@ -63,10 +63,11 @@
           </div>
           <div class="card">
             <span class="label">{{ items?.enable_web_search.des }}</span>
-            <a-switch
+            <!-- <a-switch
               :checked="configStore.config.enable_web_search"
               @change="handleChange('enable_web_search', !configStore.config.enable_web_search)"
-            />
+            /> -->
+            <a-switch :checked="configStore.config.enable_web_search" />
           </div>
           <div class="card">
             <span class="label">{{ items?.enable_reranker.des }}</span>
@@ -264,7 +265,7 @@
             </a-checkbox-group>
           </div>
           <div v-if="providerConfig.allModels.length === 0" class="modal-no-models">
-            <a-alert v-if="!modelStatus[providerConfig.provider]" type="warning" message="请在 src/.env 中配置对应的 APIKEY" />
+            <a-alert v-if="!modelStatus[providerConfig.provider]" type="warning" message="请在 src/.env 中配置对应的 APIKEY，并重新启动服务" />
             <a-alert v-else type="warning" message="该提供商暂未适配获取模型列表的方法，如果需要添加模型，请在 src/static/models.private.yml 中添加。" />
           </div>
         </div>
@@ -387,11 +388,11 @@ const handleChange = (key, e) => {
     if (!isNeedRestart.value) {
       isNeedRestart.value = true
       notification.info({
-        message: '需要重启服务',
-        description: '请点击右下角按钮重启服务',
+        message: '需要重新加载模型',
+        description: '请点击右下角按钮重新加载模型',
         placement: 'topLeft',
         duration: 0,
-        btn: h(Button, { type: 'primary', onClick: sendRestart }, '立即重启')
+        btn: h(Button, { type: 'primary', onClick: sendRestart }, '立即重新加载')
       })
     }
   }
@@ -543,7 +544,7 @@ const openProviderConfig = (provider) => {
 
 const saveProviderConfig = async () => {
   if (!modelStatus.value[providerConfig.provider]) {
-    message.error('请在 src/.env 中配置对应的 APIKEY')
+    message.error('请在 src/.env 中配置对应的 APIKEY，并重新启动服务')
     return
   }