update:绑定设备时，板子类型优先获取品牌商版名称 (#903)

* update:Server端兼容老设备缺失"client-id"请求头

* update:优化iot日志

* update:绑定设备时，板子类型优先获取品牌商版名称

* update:更新版本号

.gitignore

@@ -158,6 +158,7 @@ my_wakeup_words.mp3
 !main/xiaozhi-server/config/assets/bind_code.wav
 !main/xiaozhi-server/config/assets/bind_not_found.wav
 !main/xiaozhi-server/config/assets/bind_code/*.wav
+!main/xiaozhi-server/config/assets/max_output_size.wav
 main/manager-api/.vscode
 
 # Ignore webpack cache directory

main/manager-api/src/main/java/xiaozhi/common/constant/Constant.java

@@ -163,4 +163,9 @@ public interface Constant {
             return value;
         }
     }
+
+    /**
+     * 版本号
+     */
+    public static final String VERSION = "0.3.8";
 }

main/manager-api/src/main/java/xiaozhi/common/redis/RedisKeys.java

@@ -75,4 +75,11 @@ public class RedisKeys {
     public static String getTimbreDetailsKey(String id) {
         return "timbre:details:" + id;
     }
+
+    /**
+     * 获取版本号Key
+     */
+    public static String getVersionKey() {
+        return "system:version";
+    }
 }

main/manager-api/src/main/java/xiaozhi/common/redis/RedisUtils.java

@@ -1,11 +1,14 @@
 package xiaozhi.common.redis;
 
 import java.util.Collection;
+import java.util.Collections;
+import java.util.List;
 import java.util.Map;
 import java.util.concurrent.TimeUnit;
 
 import org.springframework.data.redis.core.HashOperations;
 import org.springframework.data.redis.core.RedisTemplate;
+import org.springframework.data.redis.core.script.DefaultRedisScript;
 import org.springframework.stereotype.Component;
 
 import jakarta.annotation.Resource;
@@ -27,7 +30,7 @@ public class RedisUtils {
     /**
      * 过期时长为1小时，单位：秒
      */
-    public final static long HOUR_ONE_EXPIRE = 60 * 60 * 1L;
+    public final static long HOUR_ONE_EXPIRE = (long) 60 * 60;
     /**
      * 过期时长为6小时，单位：秒
      */
@@ -124,4 +127,24 @@ public class RedisUtils {
     public Object rightPop(String key) {
         return redisTemplate.opsForList().rightPop(key);
     }
+
+
+    /**
+     * 清空所有 Redis 数据库中的所有键
+     */
+    public void emptyAll() {
+        // Lua 脚本 FLUSHALL是redis清空所有库的命令
+        String luaScript ="redis.call('FLUSHALL')";
+
+        // 创建 DefaultRedisScript 对象
+        DefaultRedisScript<Void> redisScript = new DefaultRedisScript<>();
+        redisScript.setScriptText(luaScript); // 设置 Lua 脚本内容
+        redisScript.setResultType(Void.class); // 设置返回值类型
+
+        // 执行 Lua 脚本
+        List<String> keys = Collections.emptyList(); // 如果脚本不依赖 key，可以传入空列表
+        redisTemplate.execute(redisScript, keys);
+
+    }
+
 }

main/manager-api/src/main/java/xiaozhi/modules/config/init/SystemInitConfig.java

@@ -5,6 +5,9 @@ import org.springframework.context.annotation.Configuration;
 import org.springframework.context.annotation.DependsOn;
 
 import jakarta.annotation.PostConstruct;
+import xiaozhi.common.constant.Constant;
+import xiaozhi.common.redis.RedisKeys;
+import xiaozhi.common.redis.RedisUtils;
 import xiaozhi.modules.config.service.ConfigService;
 import xiaozhi.modules.sys.service.SysParamsService;
 
@@ -18,8 +21,20 @@ public class SystemInitConfig {
     @Autowired
     private ConfigService configService;
 
+    @Autowired
+    private RedisUtils redisUtils;
+
     @PostConstruct
     public void init() {
+        // 检查版本号
+        String redisVersion = (String) redisUtils.get(RedisKeys.getVersionKey());
+        if (!Constant.VERSION.equals(redisVersion)) {
+            // 如果版本不一致，清空Redis
+            redisUtils.emptyAll();
+            // 存储新版本号
+            redisUtils.set(RedisKeys.getVersionKey(), Constant.VERSION);
+        }
+
         sysParamsService.initServerSecret();
         configService.getConfig(false);
     }

main/manager-api/src/main/java/xiaozhi/modules/config/service/impl/ConfigServiceImpl.java

@@ -91,6 +91,7 @@ public class ConfigServiceImpl implements ConfigService {
             }
             throw new RenException(ErrorCode.OTA_DEVICE_NOT_FOUND, "not found device");
         }
+
         // 获取智能体信息
         AgentEntity agent = agentService.getAgentById(device.getAgentId());
         if (agent == null) {
@@ -104,7 +105,9 @@ public class ConfigServiceImpl implements ConfigService {
         }
         // 构建返回数据
         Map<String, Object> result = new HashMap<>();
-
+        // 获取单台设备每天最多输出字数
+        String deviceMaxOutputSize = sysParamsService.getValue("device_max_output_size", true);
+        result.put("device_max_output_size", deviceMaxOutputSize);
         // 如果客户端已实例化模型，则不返回
         String alreadySelectedVadModelId = (String) selectedModule.get("VAD");
         if (alreadySelectedVadModelId != null && alreadySelectedVadModelId.equals(agent.getVadModelId())) {
@@ -267,6 +270,12 @@ public class ConfigServiceImpl implements ConfigService {
                         if (intentLLMModelId != null && intentLLMModelId.equals(llmModelId)) {
                             intentLLMModelId = null;
                         }
+                    } else if ("function_call".equals(map.get("type"))) {
+                        String functionStr = (String) map.get("functions");
+                        if (StringUtils.isNotBlank(functionStr)) {
+                            String[] functions = functionStr.split("\\;");
+                            map.put("functions", functions);
+                        }
                     }
                 }
                 // 如果是LLM类型，且intentLLMModelId不为空，则添加附加模型

main/manager-api/src/main/java/xiaozhi/modules/device/controller/OTAController.java

@@ -38,10 +38,13 @@ public class OTAController {
     public ResponseEntity<String> checkOTAVersion(
             @RequestBody DeviceReportReqDTO deviceReportReqDTO,
             @Parameter(name = "Device-Id", description = "设备唯一标识", required = true, in = ParameterIn.HEADER) @RequestHeader("Device-Id") String deviceId,
-            @Parameter(name = "Client-Id", description = "客户端标识", required = true, in = ParameterIn.HEADER) @RequestHeader("Client-Id") String clientId) {
+            @Parameter(name = "Client-Id", description = "客户端标识", required = false, in = ParameterIn.HEADER) @RequestHeader(value = "Client-Id", required = false) String clientId) {
-        if (StringUtils.isAnyBlank(deviceId, clientId)) {
+        if (StringUtils.isBlank(deviceId)) {
             return createResponse(DeviceReportRespDTO.createError("Device ID is required"));
         }
+        if (StringUtils.isBlank(clientId)) {
+            clientId = deviceId;
+        }
         String macAddress = deviceReportReqDTO.getMacAddress();
         boolean macAddressValid = NetworkUtil.isMacAddressValid(macAddress);
         // 设备Id和Mac地址应是一致的, 并且必须需要application字段

main/manager-api/src/main/java/xiaozhi/modules/device/service/impl/DeviceServiceImpl.java

@@ -260,8 +260,9 @@ public class DeviceServiceImpl extends BaseServiceImpl<DeviceDao, DeviceEntity>
             dataMap.put("id", deviceId);
             dataMap.put("mac_address", deviceId);
 
-            dataMap.put("board", (deviceReport.getChipModelName() != null) ? deviceReport.getChipModelName()
+            dataMap.put("board", (deviceReport.getBoard() != null && deviceReport.getBoard().getType() != null)
-                    : (deviceReport.getBoard() != null ? deviceReport.getBoard().getType() : "unknown"));
+                    ? deviceReport.getBoard().getType()
+                    : (deviceReport.getChipModelName() != null ? deviceReport.getChipModelName() : "unknown"));
             dataMap.put("app_version", (deviceReport.getApplication() != null)
                     ? deviceReport.getApplication().getVersion()
                     : null);

main/manager-api/src/main/java/xiaozhi/modules/security/controller/LoginController.java

@@ -15,6 +15,7 @@ import io.swagger.v3.oas.annotations.Operation;
 import io.swagger.v3.oas.annotations.tags.Tag;
 import jakarta.servlet.http.HttpServletResponse;
 import lombok.AllArgsConstructor;
+import xiaozhi.common.constant.Constant;
 import xiaozhi.common.exception.ErrorCode;
 import xiaozhi.common.exception.RenException;
 import xiaozhi.common.page.TokenDTO;
@@ -121,7 +122,7 @@ public class LoginController {
     @Operation(summary = "公共配置")
     public Result<Map<String, Object>> pubConfig() {
         Map<String, Object> config = new HashMap<>();
-        config.put("version", "0.3.4");
+        config.put("version", Constant.VERSION);
         config.put("allowUserRegister", sysUserService.getAllowUserRegister());
         return new Result<Map<String, Object>>().ok(config);
     }

main/manager-api/src/main/resources/db/changelog/202504181534.sql

@@ -0,0 +1,2 @@
+delete from `ai_model_config` where id = 'Intent_function_call';
+INSERT INTO `ai_model_config` VALUES ('Intent_function_call', 'Intent', 'function_call', '函数调用意图识别', 0, 1, '{\"type\": \"function_call\", \"functions\": \"change_role;get_weather;get_news;play_music\"}', NULL, NULL, 3, NULL, NULL, NULL, NULL);

main/manager-api/src/main/resources/db/changelog/202504181536.sql

@@ -0,0 +1,7 @@
+-- 调整意图识别配置
+delete from `ai_model_config` where id = 'Intent_function_call';
+INSERT INTO `ai_model_config` VALUES ('Intent_function_call', 'Intent', 'function_call', '函数调用意图识别', 0, 1, '{\"type\": \"function_call\", \"functions\": \"change_role;get_weather;get_news;play_music\"}', NULL, NULL, 3, NULL, NULL, NULL, NULL);
+
+-- 增加单台设备每天最多聊天句数
+delete from `sys_params` where  id = 105;
+INSERT INTO `sys_params` (id, param_code, param_value, value_type, param_type, remark) VALUES (105, 'device_max_output_size', '0', 'number', 1, '单台设备每天最多输出字数，0表示不限制');

main/manager-api/src/main/resources/db/changelog/db.changelog-master.yaml

@@ -58,3 +58,10 @@ databaseChangeLog:
         - sqlFile:
             encoding: utf8
             path: classpath:db/changelog/202504151206.sql
+  - changeSet:
+      id: 202504181536
+      author: John
+      changes:
+        - sqlFile:
+            encoding: utf8
+            path: classpath:db/changelog/202504181536.sql

main/manager-web/src/components/AddDeviceDialog.vue

@@ -1,5 +1,5 @@
 <template>
-  <el-dialog :visible.sync="visible" width="400px" center>
+  <el-dialog :visible="visible" @close="handleClose" width="400px" center>
     <div
       style="margin: 0 10px 10px;display: flex;align-items: center;gap: 10px;font-weight: 700;font-size: 20px;text-align: left;color: #3d4566;">
       <div
@@ -79,7 +79,10 @@ export default {
     cancel() {
       this.$emit('update:visible', false)
       this.deviceCode = ""
-    }
+    },
+    handleClose() {
+      this.$emit('update:visible', false);
+    },
   }
 }
 </script>

main/manager-web/src/components/AddModelDialog.vue

@@ -44,7 +44,7 @@
             </el-select>
           </el-form-item>
           <el-form-item label="排序号" prop="sortOrder" style="flex: 1;">
-            <el-input v-model="formData.sort" placeholder="请输入排序号" class="custom-input-bg"></el-input>
+            <el-input v-model="formData.sort" type="number" placeholder="请输入排序号" class="custom-input-bg"></el-input>
           </el-form-item>
         </div>
 

main/manager-web/src/components/AddWisdomBodyDialog.vue

@@ -1,5 +1,5 @@
 <template>
-  <el-dialog :visible.sync="visible" width="400px" center @open="handleOpen">
+  <el-dialog :visible="visible" @close="handleClose"  width="400px" center @open="handleOpen">
     <div
       style="margin: 0 10px 10px;display: flex;align-items: center;gap: 10px;font-weight: 700;font-size: 20px;text-align: left;color: #3d4566;">
       <div
@@ -66,7 +66,10 @@ export default {
     cancel() {
       this.$emit('update:visible', false)
       this.wisdomBodyName = ""
-    }
+    },
+    handleClose() {
+      this.$emit('update:visible', false);
+    },
   }
 }
 </script>

main/manager-web/src/components/DeviceItem.vue

@@ -83,7 +83,8 @@ export default {
   font-size: 10px;
   color: #5778ff;
   background: #e6ebff;
-  width: 57px;
+  width: auto;
+  padding: 0 12px;
   height: 21px;
   line-height: 21px;
   cursor: pointer;

main/manager-web/src/components/TtsModel.vue

@@ -551,28 +551,26 @@ export default {
 
 /* 备注文本 */
 ::v-deep .remark-input .el-textarea__inner {
-  background-color: #f5f5f5;
   border-radius: 4px;
   border: 1px solid #e6e6e6;
   padding: 8px 12px;
   resize: none;
   max-height: 40px !important;
   line-height: 1.5;
-}
+  background-color: transparent !important;
-
-::v-deep .remark-input .el-textarea__inner::placeholder {
-  color: black !important;
-  opacity: 0.7;
-}
-
-::v-deep .remark-input .el-textarea__inner {
-  background-color: #f4f6fa;
 }
 
 ::v-deep .remark-input .el-textarea__inner:focus {
-  background-color: #edeffb;
+  border-color: #409EFF !important;
+  outline: none;
 }
 
+::v-deep .remark-input .el-textarea__inner::placeholder {
+  color: #c0c4cc !important;
+  opacity: 1;
+}
+
+
 /* 滚动容器 */
 .scroll-wrapper {
   display: flex;
@@ -650,6 +648,12 @@ export default {
   bottom: 20px;
   padding-top: 10px;
 }
+
+.action-buttons .el-button {
+  padding: 8px 15px;
+  font-size: 11px;
+}
+
 .edit-btn,
 .delete-btn,
 .save-btn {

main/manager-web/src/views/DeviceManagement.vue

@@ -115,8 +115,8 @@ export default {
       activeSearchKeyword: "",
       currentAgentId: this.$route.query.agentId || '',
       currentPage: 1,
-      pageSize: 5,
+      pageSize: 10,
-      pageSizeOptions: [5, 10, 20, 50, 100],
+      pageSizeOptions: [10, 20, 50, 100],
       deviceList: [],
       loading: false,
       userApi: null,
@@ -283,13 +283,18 @@ export default {
           this.deviceList = data.data.map(device => {
             const bindDate = new Date(device.createDate);
             const formattedBindTime = `${bindDate.getFullYear()}-${(bindDate.getMonth() + 1).toString().padStart(2, '0')}-${bindDate.getDate().toString().padStart(2, '0')} ${bindDate.getHours().toString().padStart(2, '0')}:${bindDate.getMinutes().toString().padStart(2, '0')}:${bindDate.getSeconds().toString().padStart(2, '0')}`;
+            let formattedLastConversation = '';
+            if (device.lastConnectedAt) {
+              const lastConvoDate = new Date(device.lastConnectedAt);
+              formattedLastConversation = `${lastConvoDate.getFullYear()}-${(lastConvoDate.getMonth() + 1).toString().padStart(2, '0')}-${lastConvoDate.getDate().toString().padStart(2, '0')} ${lastConvoDate.getHours().toString().padStart(2, '0')}:${lastConvoDate.getMinutes().toString().padStart(2, '0')}:${lastConvoDate.getSeconds().toString().padStart(2, '0')}`;
+            }
             return {
               device_id: device.id,
               model: device.board,
               firmwareVersion: device.appVersion,
               macAddress: device.macAddress,
               bindTime: formattedBindTime,
-              lastConversation: device.lastConnectedAt,
+              lastConversation: formattedLastConversation,
               remark: device.alias,
               isEdit: false,
               otaSwitch: device.autoUpdate === 1,
@@ -331,7 +336,7 @@ export default {
 .main-wrapper {
   margin: 5px 22px;
   border-radius: 15px;
-  min-height: calc(100vh - 200px);
+  min-height: calc(100vh - 24vh);
   height: auto;
   max-height: 80vh;
   box-shadow: 0 2px 12px rgba(0, 0, 0, 0.1);
@@ -628,12 +633,12 @@ export default {
   flex: 1;
   display: flex;
   flex-direction: column;
-  max-height: calc(100vh - 330px);
+  max-height: calc(100vh - 40vh);
 }
 
 :deep(.el-table__body-wrapper) {
   flex: 1;
-  overflow: auto;
+  overflow-y: auto;
   max-height: none !important;
 }
 

main/manager-web/src/views/ModelConfig.vue

@@ -152,7 +152,7 @@ export default {
       ttsDialogVisible: false,
       selectedTtsModelId: '',
       modelList: [],
-      pageSizeOptions: [5, 10, 20, 50, 100],
+      pageSizeOptions: [10, 20, 50, 100],
       currentPage: 1,
       pageSize: 10,
       total: 0,
@@ -461,7 +461,7 @@ export default {
 .main-wrapper {
   margin: 5px 22px;
   border-radius: 15px;
-  min-height: calc(100vh - 235px);
+  min-height: calc(100vh - 24vh);
   height: auto;
   max-height: 80vh;
   box-shadow: 0 2px 12px rgba(0, 0, 0, 0.1);
@@ -656,7 +656,6 @@ export default {
 }
 
 .table-footer {
-  margin-top: 24px;
   display: flex;
   justify-content: space-between;
   align-items: center;
@@ -904,7 +903,7 @@ export default {
 }
 
 .data-table {
-  --table-max-height: calc(100vh - 450px);
+  --table-max-height: calc(100vh - 45vh);
   max-height: var(--table-max-height);
 }
 

main/manager-web/src/views/ParamsManagement.vue

@@ -92,8 +92,8 @@ export default {
             searchCode: "",
             paramsList: [],
             currentPage: 1,
-            pageSize: 5,
+            pageSize: 10,
-            pageSizeOptions: [5, 10, 20, 50, 100],
+            pageSizeOptions: [10, 20, 50, 100],
             total: 0,
             dialogVisible: false,
             dialogTitle: "新增参数",
@@ -330,7 +330,7 @@ export default {
 .main-wrapper {
   margin: 5px 22px;
   border-radius: 15px;
-  min-height: calc(100vh - 350px);
+  min-height: calc(100vh - 24vh);
   height: auto;
   max-height: 80vh;
   box-shadow: 0 2px 12px rgba(0, 0, 0, 0.1);
@@ -516,7 +516,7 @@ export default {
     flex-direction: column;
     .el-table__body-wrapper {
       flex: 1;
-      overflow: auto;
+      overflow-y: auto;
       max-height: none !important;
     }
 
@@ -649,7 +649,7 @@ export default {
 }
 
 .el-table {
-  --table-max-height: calc(100vh - 400px);
+  --table-max-height: calc(100vh - 40vh);
   max-height: var(--table-max-height);
 
   .el-table__body-wrapper {

main/manager-web/src/views/UserManagement.vue

@@ -99,9 +99,9 @@ export default {
       currentPassword: "",
       searchPhone: "",
       userList: [],
-      pageSizeOptions: [5, 10, 20, 50, 100],
+      pageSizeOptions: [10, 20, 50, 100],
       currentPage: 1,
-      pageSize: 5,
+      pageSize: 10,
       total: 0,
       isAllSelected: false
     };
@@ -355,7 +355,7 @@ export default {
 .main-wrapper {
   margin: 5px 22px;
   border-radius: 15px;
-  min-height: calc(100vh - 350px);
+  min-height: calc(100vh - 24vh);
   height: auto;
   max-height: 80vh;
   box-shadow: 0 2px 12px rgba(0, 0, 0, 0.1);
@@ -557,7 +557,7 @@ export default {
   flex-direction: column;
   .el-table__body-wrapper {
     flex: 1;
-    overflow: auto;
+    overflow-y: auto;
     max-height: none !important;
   }
 
@@ -674,7 +674,7 @@ export default {
 }
 
 .el-table {
-  --table-max-height: calc(100vh - 400px);
+  --table-max-height: calc(100vh - 40vh);
   max-height: var(--table-max-height);
 
   .el-table__body-wrapper {

main/manager-web/src/views/register.vue

@@ -1,5 +1,5 @@
 <template>
-  <div class="welcome">
+  <div class="welcome" @keyup.enter="register">
     <el-container style="height: 100%;">
       <!-- 保持相同的头部 -->
       <el-header>

main/manager-web/src/views/roleConfig.vue

@@ -1,88 +1,126 @@
 <template>
   <div class="welcome">
-    <HeaderBar />
+    <HeaderBar/>
-    <el-main style="padding: 16px;display: flex;flex-direction: column;">
+
-      <div style="border-radius: 16px;background: #fafcfe; border: 1px solid #e8f0ff;">
+    <div class="operation-bar">
-        <div
+      <h2 class="page-title">角色配置</h2>
-          style="padding: 15px 24px;font-weight: 700;font-size: 19px;text-align: left;color: #3d4566;display: flex;gap: 13px;align-items: center;">
+    </div>
-          <div
+
-            style="width: 37px;height: 37px;background: #5778ff;border-radius: 50%;display: flex;align-items: center;justify-content: center;">
+    <div class="main-wrapper">
-            <img loading="lazy" src="@/assets/home/setting-user.png" alt="" style="width: 19px;height: 19px;" />
+      <div class="content-panel">
-          </div>
+        <div class="content-area">
-          {{ form.agentName }}
+          <el-card class="config-card" shadow="never">
-        </div>
+            <div class="config-header">
-        <div style="height: 1px;background: #e8f0ff;" />
+              <div class="header-icon">
-        <el-form ref="form" :model="form" label-width="72px">
+                <img loading="lazy" src="@/assets/home/setting-user.png" alt="">
-          <div style="padding: 16px 24px;">
-            <div style="display: grid; grid-template-columns: 1fr 1fr; gap: 24px;">
-              <div>
-                <el-form-item label="助手昵称：">
-                  <div class="input-46" style="width: 100%;">
-                    <el-input v-model="form.agentName" />
-                  </div>
-                </el-form-item>
-                <el-form-item label="角色模版：">
-                  <div style="display: flex;gap: 8px;flex-wrap: wrap;">
-                    <div v-for="(template, index) in templates" :key="`template-${index}`" class="template-item"
-                      :class="{ 'template-loading': loadingTemplate }" @click="selectTemplate(template)">
-                      {{ template.agentName }}
-                    </div>
-                  </div>
-                </el-form-item>
-                <el-form-item label="角色介绍：">
-                  <div class="textarea-box">
-                    <el-input type="textarea" rows="5" resize="none" placeholder="请输入内容" v-model="form.systemPrompt"
-                      maxlength="2000" show-word-limit />
-                  </div>
-                </el-form-item>
-                <el-form-item label="语言编码：">
-                  <div class="input-46" style="width: 100%;">
-                    <el-input v-model="form.langCode" placeholder="请输入语言编码，如：zh_CN" maxlength="10" show-word-limit />
-                  </div>
-                </el-form-item>
-                <el-form-item label="交互语种：">
-                  <div class="input-46" style="width: 100%;">
-                    <el-input v-model="form.language" placeholder="请输入交互语种，如：中文" maxlength="10" show-word-limit />
-                  </div>
-                </el-form-item>
-              </div>
-              <div>
-                <el-form-item v-for="(model, index) in models" :key="`model-${index}`" :label="model.label"
-                  class="model-item">
-                  <el-select v-model="form.model[model.key]" filterable placeholder="请选择" class="select-field">
-                    <el-option v-for="(item, optionIndex) in modelOptions[model.type]"
-                      :key="`option-${index}-${optionIndex}`" :label="item.label" :value="item.value" />
-                  </el-select>
-                </el-form-item>
-                <el-form-item label="角色音色：">
-                  <div style="display: flex;gap: 8px;align-items: center;">
-                    <div class="input-46" style="width: 100%;">
-                      <el-select v-model="form.ttsVoiceId" placeholder="请选择" style="width: 100%;">
-                        <el-option v-for="(item, index) in voiceOptions" :key="`voice-${index}`" :label="item.label"
-                          :value="item.value" />
-                      </el-select>
-                    </div>
-                  </div>
-                </el-form-item>
               </div>
+              <span class="header-title">{{ form.agentName }}</span>
             </div>
-          </div>
+            <div class="divider"></div>
-        </el-form>
+
-        <div style="display: flex;padding: 16px;gap: 8px;align-items: center;">
+            <el-form ref="form" :model="form" label-width="72px">
-          <div class="save-btn" @click="saveConfig">
+              <div class="form-content">
-            保存配置
+                <div class="form-grid">
-          </div>
+                  <div class="form-column">
-          <div class="reset-btn" @click="resetConfig">
+                    <el-form-item label="助手昵称：">
-            重制
+                      <el-input v-model="form.agentName" class="form-input"/>
-          </div>
+                    </el-form-item>
-          <div class="clear-text">
+                    <el-form-item label="角色模版：">
-            <img loading="lazy" src="@/assets/home/red-info.png" alt="" style="width: 19px;height: 19px;" />
+                      <div class="template-container">
-            保存配置后，需要重启设备，新的配置才会生效。
+                        <div
-          </div>
+                            v-for="(template, index) in templates"
+                            :key="`template-${index}`"
+                            class="template-item"
+                            :class="{ 'template-loading': loadingTemplate }"
+                            @click="selectTemplate(template)"
+                        >
+                          {{ template.agentName }}
+                        </div>
+                      </div>
+                    </el-form-item>
+                    <el-form-item label="角色介绍：">
+                      <el-input
+                          type="textarea"
+                          rows="5"
+                          resize="none"
+                          placeholder="请输入内容"
+                          v-model="form.systemPrompt"
+                          maxlength="2000"
+                          show-word-limit
+                          class="form-textarea"
+                      />
+                    </el-form-item>
+                    <el-form-item label="语言编码：">
+                      <el-input
+                          v-model="form.langCode"
+                          placeholder="请输入语言编码，如：zh_CN"
+                          maxlength="10"
+                          show-word-limit
+                          class="form-input"
+                      />
+                    </el-form-item>
+                    <el-form-item label="交互语种：">
+                      <el-input
+                          v-model="form.language"
+                          placeholder="请输入交互语种，如：中文"
+                          maxlength="10"
+                          show-word-limit
+                          class="form-input"
+                      />
+                    </el-form-item>
+                    <div class="action-bar">
+              <el-button type="primary" class="save-btn" @click="saveConfig">保存配置</el-button>
+              <el-button class="reset-btn" @click="resetConfig">重置</el-button>
+              <div class="hint-text">
+                <img loading="lazy" src="@/assets/home/red-info.png" alt="">
+                <span>保存配置后，需要重启设备，新的配置才会生效。</span>
+              </div>
+</div>
+                  </div>
+                  <div class="form-column">
+                    <el-form-item
+                        v-for="(model, index) in models"
+                        :key="`model-${index}`"
+                        :label="model.label"
+                        class="model-item"
+                    >
+                      <el-select
+                          v-model="form.model[model.key]"
+                          filterable
+                          placeholder="请选择"
+                          class="form-select"
+                      >
+                        <el-option
+                            v-for="(item, optionIndex) in modelOptions[model.type]"
+                            :key="`option-${index}-${optionIndex}`"
+                            :label="item.label"
+                            :value="item.value"
+                        />
+                      </el-select>
+                    </el-form-item>
+                    <el-form-item label="角色音色：">
+                      <el-select
+                          v-model="form.ttsVoiceId"
+                          placeholder="请选择"
+                          class="form-select"
+                      >
+                        <el-option
+                            v-for="(item, index) in voiceOptions"
+                            :key="`voice-${index}`"
+                            :label="item.label"
+                            :value="item.value"
+                        />
+                      </el-select>
+                    </el-form-item>
+                  </div>
+                </div>
+              </div>
+            </el-form>
+
+          </el-card>
         </div>
       </div>
-
+    </div>
-    </el-main>
   </div>
 </template>
 
@@ -90,10 +128,9 @@
 import Api from '@/apis/api';
 import HeaderBar from "@/components/HeaderBar.vue";
 
-
 export default {
   name: 'RoleConfigPage',
-  components: { HeaderBar },
+  components: {HeaderBar},
   data() {
     return {
       form: {
@@ -114,12 +151,12 @@ export default {
         }
       },
       models: [
-        { label: '语音活动检测(VAD)', key: 'vadModelId', type: 'VAD' },
+        {label: '语音活动检测(VAD)', key: 'vadModelId', type: 'VAD'},
-        { label: '语音识别(ASR)', key: 'asrModelId', type: 'ASR' },
+        {label: '语音识别(ASR)', key: 'asrModelId', type: 'ASR'},
-        { label: '大语言模型(LLM)', key: 'llmModelId', type: 'LLM' },
+        {label: '大语言模型(LLM)', key: 'llmModelId', type: 'LLM'},
-        { label: '意图识别(Intent)', key: 'intentModelId', type: 'Intent' },
+        {label: '意图识别(Intent)', key: 'intentModelId', type: 'Intent'},
-        { label: '记忆(Memory)', key: 'memModelId', type: 'Memory' },
+        {label: '记忆(Memory)', key: 'memModelId', type: 'Memory'},
-        { label: '语音合成(TTS)', key: 'ttsModelId', type: 'TTS' },
+        {label: '语音合成(TTS)', key: 'ttsModelId', type: 'TTS'},
       ],
       modelOptions: {},
       templates: [],
@@ -144,7 +181,7 @@ export default {
         language: this.form.language,
         sort: this.form.sort
       };
-      Api.agent.updateAgentConfig(this.$route.query.agentId, configData, ({ data }) => {
+      Api.agent.updateAgentConfig(this.$route.query.agentId, configData, ({data}) => {
         if (data.code === 0) {
           this.$message.success({
             message: '配置保存成功',
@@ -164,7 +201,6 @@ export default {
         cancelButtonText: '取消',
         type: 'warning'
       }).then(() => {
-        // 重置表单
         this.form = {
           agentCode: "",
           agentName: "",
@@ -187,10 +223,10 @@ export default {
           showClose: true
         })
       }).catch(() => {
-      })
+      });
     },
     fetchTemplates() {
-      Api.agent.getAgentTemplate(({ data }) => {
+      Api.agent.getAgentTemplate(({data}) => {
         if (data.code === 0) {
           this.templates = data.data;
         } else {
@@ -235,7 +271,7 @@ export default {
       };
     },
     fetchAgentConfig(agentId) {
-      Api.agent.getDeviceConfig(agentId, ({ data }) => {
+      Api.agent.getDeviceConfig(agentId, ({data}) => {
         if (data.code === 0) {
           this.form = {
             ...this.form,
@@ -255,9 +291,8 @@ export default {
       });
     },
     fetchModelOptions() {
-      // 为每个模型类型获取选项
       this.models.forEach(model => {
-        Api.model.getModelNames(model.type, '', ({ data }) => {
+        Api.model.getModelNames(model.type, '', ({data}) => {
           if (data.code === 0) {
             this.$set(this.modelOptions, model.type, data.data.map(item => ({
               value: item.id,
@@ -274,7 +309,7 @@ export default {
         this.voiceOptions = [];
         return;
       }
-      Api.model.getModelVoices(modelId, '', ({ data }) => {
+      Api.model.getModelVoices(modelId, '', ({data}) => {
         if (data.code === 0 && data.data) {
           this.voiceOptions = data.data.map(voice => ({
             value: voice.id,
@@ -289,7 +324,6 @@ export default {
   watch: {
     'form.model.ttsModelId': {
       handler(newVal, oldVal) {
-        console.log('TTS模型变化:', newVal);
         if (oldVal && newVal !== oldVal) {
           this.form.ttsVoiceId = '';
           this.fetchVoiceOptions(newVal);
@@ -325,60 +359,131 @@ export default {
   min-height: 506px;
   height: 100vh;
   display: flex;
+  position: relative;
   flex-direction: column;
-  background: linear-gradient(145deg, #e6eeff, #eff0ff);
+  background: linear-gradient(to bottom right, #dce8ff, #e4eeff, #e6cbfd);
   background-size: cover;
-  /* 确保背景图像覆盖整个元素 */
-  background-position: center;
-  /* 从顶部中心对齐 */
   -webkit-background-size: cover;
-  /* 兼容老版本WebKit浏览器 */
   -o-background-size: cover;
-  /* 兼容老版本Opera浏览器 */
+  overflow: hidden;
 }
 
-.el-form-item ::v-deep .el-form-item__label {
+.operation-bar {
-  font-size: 10px !important;
+  display: flex;
-  color: #3d4566 !important;
+  justify-content: space-between;
-  font-weight: 400;
+  align-items: center;
-  line-height: 22px;
+  padding: 16px 24px;
-  padding-bottom: 2px;
 }
 
-.select-field {
+.page-title {
-  width: 100%;
+  font-size: 24px;
-  max-width: 720px;
+  margin: 0;
-  border: 1px solid #e4e6ef;
+  color: #2c3e50;
-  background: #f6f8fb;
-  border-radius: 8px;
-  height: 36px !important;
 }
 
-.audio-box {
+.main-wrapper {
+  margin: 5px 22px;
+  border-radius: 15px;
+  height: calc(100vh - 24vh);
+  box-shadow: 0 2px 12px rgba(0, 0, 0, 0.1);
+  position: relative;
+  background: rgba(237, 242, 255, 0.5);
+  display: flex;
+  flex-direction: column;
+}
+
+.content-panel {
   flex: 1;
-  height: 37px;
+  display: flex;
-  border-radius: 20px;
+  overflow: hidden;
-  border: 1px solid #e4e6ef;
+  height: 100%;
+  border-radius: 15px;
+  background: transparent;
+  border: 1px solid #fff;
 }
 
-.clear-btn {
+.content-area {
-  width: 48px;
+  flex: 1;
-  height: 19px;
+  height: 100%;
-  background: #fd8383;
+  min-width: 600px;
-  border-radius: 10px;
+  overflow: auto;
-  line-height: 19px;
+  background-color: white;
-  font-size: 11px;
+  display: flex;
-  color: #fff;
+  flex-direction: column;
-  cursor: pointer;
 }
 
-.clear-text {
+.config-card {
-  color: #979db1;
+  background: white;
-  font-size: 11px;
+  border: none;
+  box-shadow: none;
+  display: flex;
+  flex-direction: column;
+  flex: 1;
+  overflow-y: auto;
+}
+
+.config-header {
   display: flex;
   align-items: center;
+  gap: 13px;
+  padding: 0 0 5px 0;
+  font-weight: 700;
+  font-size: 19px;
+  color: #3d4566;
+}
+
+.header-icon {
+  width: 37px;
+  height: 37px;
+  background: #5778ff;
+  border-radius: 50%;
+  display: flex;
+  align-items: center;
+  justify-content: center;
+}
+
+.header-icon img {
+  width: 19px;
+  height: 19px;
+}
+
+.divider {
+  height: 1px;
+  background: #e8f0ff;
+}
+
+.form-content {
+  padding: 20px 0;
+}
+
+.form-grid {
+  display: grid;
+  grid-template-columns: 1fr 1fr;
+  gap: 20px;
+}
+
+.form-column {
+  display: flex;
+  flex-direction: column;
+  gap: 6px;
+}
+
+.form-input {
+  width: 100%;
+}
+
+.form-select {
+  width: 100%;
+}
+
+.form-textarea {
+  width: 100%;
+}
+
+.template-container {
+  display: flex;
   gap: 8px;
-  margin-left: 16px;
+  flex-wrap: wrap;
 }
 
 .template-item {
@@ -399,47 +504,64 @@ export default {
   background-color: #d0d8ff;
 }
 
-.prompt-bottom {
+.action-bar {
-  margin-bottom: 4px;
   display: flex;
-  justify-content: space-between;
+  flex-wrap: wrap;
-  padding: 0 16px;
+  gap: 8px;
+  margin-top: 20px;
   align-items: center;
 }
 
-.input-46 {
+.action-bar {
-  border: 1px solid #e4e6ef;
+  .el-button.save-btn {
-  background: #f6f8fb;
+    background: #5778ff;
-  border-radius: 8px;
+    color: white;
-  height: 36px !important;
+    border: none;
+    border-radius: 18px;
+    padding: 10px 20px;
+    width: 100px;
+    height: 35px;
+    font-size: 14px;
+  }
+
+  .el-button.reset-btn {
+    background: #e6ebff;
+    color: #5778ff;
+    border: 1px solid #adbdff;
+    border-radius: 18px;
+    padding: 10px 20px;
+  }
 }
 
-.save-btn,
+.hint-text {
-.reset-btn {
+  display: flex;
-  width: 112px;
+  align-items: center;
-  height: 37px;
+  gap: 8px;
-  border-radius: 18px;
+  color: #979db1;
-  line-height: 37px;
+  font-size: 11px;
-  box-sizing: border-box;
+  margin-left: 16px;
-  cursor: pointer;
-  font-size: 11px
 }
 
-.save-btn {
+.hint-text img {
-  border-radius: 18px;
+  width: 19px;
-  background: #5778ff;
+  height: 19px;
-  color: #fff;
 }
 
-.reset-btn {
+::v-deep .el-form-item__label {
-  border: 1px solid #adbdff;
+  font-size: 10px !important;
-  background: #e6ebff;
+  color: #3d4566 !important;
-  color: #5778ff;
+  font-weight: 400;
+  line-height: 22px;
+  padding-bottom: 2px;
 }
 
-.textarea-box {
+::v-deep .el-textarea .el-input__count {
-  border: 1px solid #e4e6ef;
+  color: #909399;
-  border-radius: 8px;
+  background: none;
-  background: #f6f8fb;
+  position: absolute;
+  font-size: 12px;
+  bottom: -10px;
+  right: 21px;
 }
-</style>
+
+</style>

main/xiaozhi-server/config.yaml

@@ -147,7 +147,7 @@ selected_module:
   Memory: nomem
   # 意图识别模块开启后，可以播放音乐、控制音量、识别退出指令。
   # 不想开通意图识别，就设置成：nointent
-  # 意图识别可使用intent_llm，如果你的LLM是DifyLLM或CozeLLM，建议使用这个。优点：通用性强，缺点：增加串行前置意图识别模块，会增加处理时间，这个意图识别暂时不支持控制音量大小等iot操作
+  # 意图识别可使用intent_llm。优点：通用性强，缺点：增加串行前置意图识别模块，会增加处理时间，这个意图识别暂时不支持控制音量大小等iot操作
   # 意图识别可使用function_call，缺点：需要所选择的LLM支持function_call，优点：按需调用工具、速度快，理论上能全部操作所有iot指令
   # 默认免费的ChatGLMLLM就已经支持function_call，但是如果像追求稳定建议把LLM设置成：DoubaoLLM，使用的具体model_name是：doubao-pro-32k-functioncall-241028
   Intent: function_call
@@ -163,7 +163,7 @@ Intent:
     type: intent_llm
     # 配备意图识别独立的思考模型
     # 如果这里不填，则会默认使用selected_module.LLM的模型作为意图识别的思考模型
-    # 如果你的selected_module.LLM选择了DifyLLM或CozeLLM，这里最好使用独立的LLM作为意图识别，例如使用免费的ChatGLMLLM
+    # 如果你的不想使用selected_module.LLM意图识别，这里最好使用独立的LLM作为意图识别，例如使用免费的ChatGLMLLM
     llm: ChatGLMLLM
   function_call:
     # 不需要动type

main/xiaozhi-server/config/config_loader.py

@@ -1,18 +1,7 @@
 import os
 import argparse
-import requests
 import yaml
-import time
+from config.manage_api_client import init_service, get_server_config, get_agent_models
-
-
-class DeviceNotFoundException(Exception):
-    pass
-
-
-class DeviceBindException(Exception):
-    def __init__(self, bind_code):
-        self.bind_code = bind_code
-        super().__init__(f"设备绑定异常，绑定码: {bind_code}")
 
 
 # 添加全局配置缓存
@@ -65,97 +54,27 @@ def get_config_file():
     return config_file
 
 
-def _make_api_request(api_url, secret, endpoint, json_data=None):
-    """执行API请求的通用函数
-
-    Args:
-        api_url: API的基础URL
-        secret: API密钥
-        endpoint: API端点
-        json_data: 请求的JSON数据
-
-    Returns:
-        dict: API返回的数据
-
-    Raises:
-        Exception: 当请求失败时抛出异常
-    """
-    if not api_url or not secret:
-        raise Exception("manager-api的url或secret配置错误")
-
-    if "你" in secret:
-        raise Exception("请先配置manager-api的secret")
-
-    max_retries = 10
-    retry_delay = 2  # 秒
-
-    for attempt in range(max_retries):
-        try:
-            response = requests.post(f"{api_url}{endpoint}", json=json_data)
-            if response.status_code == 200:
-                result = response.json()
-                if result.get("code") == 10041:
-                    raise DeviceNotFoundException(result.get("msg"))
-                elif result.get("code") == 10042:
-                    raise DeviceBindException(result.get("msg"))
-                elif result.get("code") != 0:
-                    raise Exception(f"API返回错误: {result.get('msg', '未知错误')}")
-                return result.get("data")
-
-            error_msg = f"manager-api请求失败，状态码: {response.status_code}"
-            try:
-                error_data = response.json()
-                if "msg" in error_data:
-                    error_msg = f"{error_msg}, 错误信息: {error_data['msg']}"
-            except:
-                error_msg = f"{error_msg}, 响应内容: {response.text}"
-
-            if attempt < max_retries - 1:
-                print(f"请求manager-api失败，正在重试 ({attempt + 1}/{max_retries})...")
-                time.sleep(retry_delay)
-            else:
-                raise Exception(error_msg)
-
-        except requests.exceptions.RequestException as e:
-            if attempt < max_retries - 1:
-                print(f"请求manager-api异常，正在重试 ({attempt + 1}/{max_retries})...")
-                time.sleep(retry_delay)
-            else:
-                raise Exception(f"manager-api请求异常: {str(e)}")
-
-
 def get_config_from_api(config):
     """从Java API获取配置"""
-    api_url = config["manager-api"].get("url", "")
+    # 初始化API客户端
-    secret = config["manager-api"].get("secret", "")
+    init_service(config)
+
+    # 获取服务器配置
+    config_data = get_server_config()
+    if config_data is None:
+        raise Exception("Failed to fetch server config from API")
 
-    config_data = _make_api_request(
-        api_url, secret, "/config/server-base", {"secret": secret}
-    )
     config_data["read_config_from_api"] = True
     config_data["manager-api"] = {
-        "url": api_url,
+        "url": config["manager-api"].get("url", ""),
-        "secret": secret,
+        "secret": config["manager-api"].get("secret", ""),
     }
     return config_data
 
 
 def get_private_config_from_api(config, device_id, client_id):
     """从Java API获取私有配置"""
-    api_url = config["manager-api"].get("url", "")
+    return get_agent_models(device_id, client_id, config["selected_module"])
-    secret = config["manager-api"].get("secret", "")
-
-    return _make_api_request(
-        api_url,
-        secret,
-        "/config/agent-models",
-        {
-            "secret": secret,
-            "macAddress": device_id,
-            "clientId": client_id,
-            "selectedModule": config["selected_module"],
-        },
-    )
 
 
 def ensure_directories(config):

main/xiaozhi-server/config/logger.py

@@ -3,7 +3,7 @@ import sys
 from loguru import logger
 from config.config_loader import load_config
 
-SERVER_VERSION = "0.3.4"
+SERVER_VERSION = "0.3.8"
 
 
 def get_module_abbreviation(module_name, module_dict):

main/xiaozhi-server/config/manage_api_client.py

@@ -0,0 +1,154 @@
+import os
+import time
+from typing import Optional, Dict
+
+import httpx
+
+TAG = __name__
+
+
+class DeviceNotFoundException(Exception):
+    pass
+
+
+class DeviceBindException(Exception):
+    def __init__(self, bind_code):
+        self.bind_code = bind_code
+        super().__init__(f"设备绑定异常，绑定码: {bind_code}")
+
+
+class ManageApiClient:
+    _instance = None
+    _client = None
+    _secret = None
+
+    def __new__(cls, config):
+        """单例模式确保全局唯一实例，并支持传入配置参数"""
+        if cls._instance is None:
+            cls._instance = super().__new__(cls)
+            cls._init_client(config)
+        return cls._instance
+
+    @classmethod
+    def _init_client(cls, config):
+        """初始化持久化连接池"""
+        cls.config = config.get("manager-api")
+
+        if not cls.config:
+            raise Exception("manager-api配置错误")
+
+        if not cls.config.get("url") or not cls.config.get("secret"):
+            raise Exception("manager-api的url或secret配置错误")
+
+        if "你" in cls.config.get("secret"):
+            raise Exception("请先配置manager-api的secret")
+
+        cls._secret = cls.config.get("secret")
+        cls.max_retries = cls.config.get("max_retries", 6)  # 最大重试次数
+        cls.retry_delay = cls.config.get("retry_delay", 10)  # 初始重试延迟(秒)
+        # NOTE(goody): 2025/4/16 http相关资源统一管理，后续可以增加线程池或者超时
+        # 后续也可以统一配置apiToken之类的走通用的Auth
+        cls._client = httpx.Client(
+            base_url=cls.config.get("url"),
+            headers={
+                "User-Agent": f"PythonClient/2.0 (PID:{os.getpid()})",
+                "Accept": "application/json",
+            },
+            timeout=cls.config.get("timeout", 30),  # 默认超时时间30秒
+        )
+
+    @classmethod
+    def _request(cls, method: str, endpoint: str, **kwargs) -> Dict:
+        """发送单次HTTP请求并处理响应"""
+        endpoint = endpoint.lstrip("/")
+        response = cls._client.request(method, endpoint, **kwargs)
+        response.raise_for_status()
+
+        result = response.json()
+
+        # 处理API返回的业务错误
+        if result.get("code") == 10041:
+            raise DeviceNotFoundException(result.get("msg"))
+        elif result.get("code") == 10042:
+            raise DeviceBindException(result.get("msg"))
+        elif result.get("code") != 0:
+            raise Exception(f"API返回错误: {result.get('msg', '未知错误')}")
+
+        # 返回成功数据
+        return result.get("data") if result.get("code") == 0 else None
+
+    @classmethod
+    def _should_retry(cls, exception: Exception) -> bool:
+        """判断异常是否应该重试"""
+        # 网络连接相关错误
+        if isinstance(
+            exception, (httpx.ConnectError, httpx.TimeoutException, httpx.NetworkError)
+        ):
+            return True
+
+        # HTTP状态码错误
+        if isinstance(exception, httpx.HTTPStatusError):
+            status_code = exception.response.status_code
+            return status_code in [408, 429, 500, 502, 503, 504]
+
+        return False
+
+    @classmethod
+    def _execute_request(cls, method: str, endpoint: str, **kwargs) -> Dict:
+        """带重试机制的请求执行器"""
+        retry_count = 0
+
+        while retry_count <= cls.max_retries:
+            try:
+                # 执行请求
+                return cls._request(method, endpoint, **kwargs)
+            except Exception as e:
+                # 判断是否应该重试
+                if retry_count < cls.max_retries and cls._should_retry(e):
+                    retry_count += 1
+                    print(
+                        f"{method} {endpoint} 请求失败，将在 {cls.retry_delay:.1f} 秒后进行第 {retry_count} 次重试"
+                    )
+                    time.sleep(cls.retry_delay)
+                    continue
+                else:
+                    # 不重试，直接抛出异常
+                    raise
+
+    @classmethod
+    def safe_close(cls):
+        """安全关闭连接池"""
+        if cls._client:
+            cls._client.close()
+            cls._instance = None
+
+
+def get_server_config() -> Optional[Dict]:
+    """获取服务器基础配置"""
+    return ManageApiClient._instance._execute_request(
+        "POST", "/config/server-base", json={"secret": ManageApiClient._secret}
+    )
+
+
+def get_agent_models(
+    mac_address: str, client_id: str, selected_module: Dict
+) -> Optional[Dict]:
+    """获取代理模型配置"""
+    return ManageApiClient._instance._execute_request(
+        "POST",
+        "/config/agent-models",
+        json={
+            "secret": ManageApiClient._secret,
+            "macAddress": mac_address,
+            "clientId": client_id,
+            "selectedModule": selected_module,
+        },
+    )
+
+
+def init_service(config):
+    ManageApiClient(config)
+
+
+def manage_api_http_safe_close():
+    ManageApiClient.safe_close()

main/xiaozhi-server/core/connection.py

@@ -27,11 +27,9 @@ from core.handle.functionHandler import FunctionHandler
 from plugins_func.register import Action, ActionResponse
 from core.auth import AuthMiddleware, AuthenticationError
 from core.mcp.manager import MCPManager
-from config.config_loader import (
+from config.config_loader import get_private_config_from_api
-    get_private_config_from_api,
+from config.manage_api_client import DeviceNotFoundException, DeviceBindException
-    DeviceNotFoundException,
+from core.utils.output_counter import add_device_output
-    DeviceBindException,
-)
 
 TAG = __name__
 
@@ -60,6 +58,7 @@ class ConnectionHandler:
         self.session_id = None
         self.prompt = None
         self.welcome_msg = None
+        self.max_output_size = 0
 
         # 客户端状态相关
         self.client_abort = False
@@ -112,10 +111,36 @@ class ConnectionHandler:
         self.close_after_chat = False  # 是否在聊天结束后关闭连接
         self.use_function_call_mode = False
 
+        self.timeout_task = None
+        self.timeout_seconds = (
+            int(self.config.get("close_connection_no_voice_time", 120)) + 60
+        )  # 在原来第一道关闭的基础上加60秒，进行二道关闭
+
     async def handle_connection(self, ws):
         try:
             # 获取并验证headers
             self.headers = dict(ws.request.headers)
+
+            if self.headers.get("device-id", None) is None:
+                # 尝试从 URL 的查询参数中获取 device-id
+                from urllib.parse import parse_qs, urlparse
+
+                # 从 WebSocket 请求中获取路径
+                request_path = ws.request.path
+                if not request_path:
+                    self.logger.bind(tag=TAG).error("无法获取请求路径")
+                    return
+                parsed_url = urlparse(request_path)
+                query_params = parse_qs(parsed_url.query)
+                if "device-id" in query_params:
+                    self.headers["device-id"] = query_params["device-id"][0]
+                    self.headers["client-id"] = query_params["client-id"][0]
+                else:
+                    self.logger.bind(tag=TAG).error(
+                        "无法从请求头和URL查询参数中获取device-id"
+                    )
+                    return
+
             # 获取客户端ip地址
             self.client_ip = ws.remote_address[0]
             self.logger.bind(tag=TAG).info(
@@ -129,12 +154,17 @@ class ConnectionHandler:
             self.websocket = ws
             self.session_id = str(uuid.uuid4())
 
+            # 启动超时检查任务
+            self.timeout_task = asyncio.create_task(self._check_timeout())
+
             self.welcome_msg = self.config["xiaozhi"]
             self.welcome_msg["session_id"] = self.session_id
             await self.websocket.send(json.dumps(self.welcome_msg))
 
+            # 获取差异化配置
+            private_config = self._initialize_private_config()
             # 异步初始化
-            self.executor.submit(self._initialize_components)
+            self.executor.submit(self._initialize_components, private_config)
             # tts 消化线程
             self.tts_priority_thread = threading.Thread(
                 target=self._tts_priority_thread, daemon=True
@@ -174,19 +204,23 @@ class ConnectionHandler:
 
     async def _route_message(self, message):
         """消息路由"""
+        # 重置超时计时器
+        if self.timeout_task:
+            self.timeout_task.cancel()
+            self.timeout_task = asyncio.create_task(self._check_timeout())
+
         if isinstance(message, str):
             await handleTextMessage(self, message)
         elif isinstance(message, bytes):
             await handleAudioMessage(self, message)
 
-    def _initialize_components(self):
+    def _initialize_components(self, private_config):
         """初始化组件"""
-        self._initialize_models()
+        if private_config is not None:
-
+            self._initialize_models(private_config)
-        """加载提示词"""
+        else:
-        self.prompt = self.config["prompt"]
+            self.prompt = self.config["prompt"]
-        self.dialogue.put(Message(role="system", content=self.prompt))
+            self.change_system_prompt(self.prompt)
-
         """加载记忆"""
         self._initialize_memory()
         """加载意图识别"""
@@ -199,20 +233,23 @@ class ConnectionHandler:
 
             self.dialogue.update_system_message(self.prompt)
 
-    def _initialize_models(self):
+    def _initialize_private_config(self):
         read_config_from_api = self.config.get("read_config_from_api", False)
         """如果是从配置文件获取，则进行二次实例化"""
         if not read_config_from_api:
             return
         """从接口获取差异化的配置进行二次实例化，非全量重新实例化"""
         try:
+            begin_time = time.time()
             private_config = get_private_config_from_api(
                 self.config,
-                self.headers.get("device-id", None),
+                self.headers.get("device-id"),
-                self.headers.get("client-id", None),
+                self.headers.get("client-id", self.headers.get("device-id")),
             )
             private_config["delete_audio"] = bool(self.config.get("delete_audio", True))
-            self.logger.bind(tag=TAG).info(f"获取差异化配置成功: {private_config}")
+            self.logger.bind(tag=TAG).info(
+                f"{time.time() - begin_time} 秒，获取差异化配置成功: {private_config}"
+            )
         except DeviceNotFoundException as e:
             self.need_bind = True
             private_config = {}
@@ -225,8 +262,37 @@ class ConnectionHandler:
             self.logger.bind(tag=TAG).error(f"获取差异化配置失败: {e}")
             private_config = {}
 
-        init_vad, init_asr, init_llm, init_tts, init_memory, init_intent = (
+        init_tts = False
-            False,
+        if private_config.get("TTS", None) is not None:
+            init_tts = True
+            self.config["TTS"] = private_config["TTS"]
+            self.config["selected_module"]["TTS"] = private_config["selected_module"][
+                "TTS"
+            ]
+
+        try:
+            modules = initialize_modules(
+                self.logger,
+                private_config,
+                False,
+                False,
+                False,
+                init_tts,
+                False,
+                False,
+            )
+        except Exception as e:
+            self.logger.bind(tag=TAG).error(f"初始化组件失败: {e}")
+            modules = {}
+        if modules.get("tts", None) is not None:
+            self.tts = modules["tts"]
+        if modules.get("prompt", None) is not None:
+            self.change_system_prompt(modules["prompt"])
+            private_config["prompt"] = None
+        return private_config
+
+    def _initialize_models(self, private_config):
+        init_vad, init_asr, init_llm, init_memory, init_intent = (
             False,
             False,
             False,
@@ -251,12 +317,6 @@ class ConnectionHandler:
             self.config["selected_module"]["LLM"] = private_config["selected_module"][
                 "LLM"
             ]
-        if private_config.get("TTS", None) is not None:
-            init_tts = True
-            self.config["TTS"] = private_config["TTS"]
-            self.config["selected_module"]["TTS"] = private_config["selected_module"][
-                "TTS"
-            ]
         if private_config.get("Memory", None) is not None:
             init_memory = True
             self.config["Memory"] = private_config["Memory"]
@@ -269,6 +329,8 @@ class ConnectionHandler:
             self.config["selected_module"]["Intent"] = private_config[
                 "selected_module"
             ]["Intent"]
+        if private_config.get("device_max_output_size", None) is not None:
+            self.max_output_size = int(private_config["device_max_output_size"])
         try:
             modules = initialize_modules(
                 self.logger,
@@ -276,7 +338,7 @@ class ConnectionHandler:
                 init_vad,
                 init_asr,
                 init_llm,
-                init_tts,
+                False,
                 init_memory,
                 init_intent,
             )
@@ -287,16 +349,12 @@ class ConnectionHandler:
             self.vad = modules["vad"]
         if modules.get("asr", None) is not None:
             self.asr = modules["asr"]
-        if modules.get("tts", None) is not None:
-            self.tts = modules["tts"]
         if modules.get("llm", None) is not None:
             self.llm = modules["llm"]
         if modules.get("intent", None) is not None:
             self.intent = modules["intent"]
         if modules.get("memory", None) is not None:
             self.memory = modules["memory"]
-        if modules.get("prompt", None) is not None:
-            self.change_system_prompt(modules["prompt"])
 
     def _initialize_memory(self):
         """初始化记忆模块"""
@@ -477,16 +535,19 @@ class ConnectionHandler:
         function_id = None
         function_arguments = ""
         content_arguments = ""
+
         for response in llm_responses:
             content, tools_call = response
+
             if "content" in response:
                 content = response["content"]
                 tools_call = None
             if content is not None and len(content) > 0:
-                if len(response_message) <= 0 and (
+                content_arguments += content
-                    content == "```" or "<tool_call>" in content
+
-                ):
+            if not tool_call_flag and content_arguments.startswith("<tool_call>"):
-                    tool_call_flag = True
+                # print("content_arguments", content_arguments)
+                tool_call_flag = True
 
             if tools_call is not None:
                 tool_call_flag = True
@@ -498,9 +559,7 @@ class ConnectionHandler:
                     function_arguments += tools_call[0].function.arguments
 
             if content is not None and len(content) > 0:
-                if tool_call_flag:
+                if not tool_call_flag:
-                    content_arguments += content
-                else:
                     response_message.append(content)
 
                     if self.client_abort:
@@ -561,10 +620,9 @@ class ConnectionHandler:
                     self.logger.bind(tag=TAG).error(
                         f"function call error: {content_arguments}"
                     )
-                else:
-                    function_arguments = json.loads(function_arguments)
             if not bHasError:
-                self.logger.bind(tag=TAG).info(
+                response_message.clear()
+                self.logger.bind(tag=TAG).debug(
                     f"function_name={function_name}, function_id={function_id}, function_arguments={function_arguments}"
                 )
                 function_call_data = {
@@ -659,7 +717,6 @@ class ConnectionHandler:
             self.tts_queue.put(future)
             self.dialogue.put(Message(role="assistant", content=text))
         elif result.action == Action.REQLLM:  # 调用函数后再请求llm生成回复
-
             text = result.result
             if text is not None and len(text) > 0:
                 function_id = function_call_data["id"]
@@ -686,18 +743,14 @@ class ConnectionHandler:
                     Message(role="tool", tool_call_id=function_id, content=text)
                 )
                 self.chat_with_function_calling(text, tool_call=True)
-        elif result.action == Action.NOTFOUND:
+        elif result.action == Action.NOTFOUND or result.action == Action.ERROR:
             text = result.result
             self.recode_first_last_text(text, text_index)
             future = self.executor.submit(self.speak_and_play, text, text_index)
             self.tts_queue.put(future)
             self.dialogue.put(Message(role="assistant", content=text))
         else:
-            text = result.result
+            pass
-            self.recode_first_last_text(text, text_index)
-            future = self.executor.submit(self.speak_and_play, text, text_index)
-            self.tts_queue.put(future)
-            self.dialogue.put(Message(role="assistant", content=text))
 
     def _tts_priority_thread(self):
         while not self.stop_event.is_set():
@@ -795,6 +848,8 @@ class ConnectionHandler:
             self.logger.bind(tag=TAG).error(f"tts转换失败，{text}")
             return None, text, text_index
         self.logger.bind(tag=TAG).debug(f"TTS 文件生成完毕: {tts_file}")
+        if self.max_output_size > 0:
+            add_device_output(self.headers.get("device-id"), len(text))
         return tts_file, text, text_index
 
     def clearSpeakStatus(self):
@@ -811,6 +866,11 @@ class ConnectionHandler:
 
     async def close(self, ws=None):
         """资源清理方法"""
+        # 取消超时任务
+        if self.timeout_task:
+            self.timeout_task.cancel()
+            self.timeout_task = None
+
         # 清理MCP资源
         if hasattr(self, "mcp_manager") and self.mcp_manager:
             await self.mcp_manager.cleanup_all()
@@ -864,3 +924,15 @@ class ConnectionHandler:
             self.close_after_chat = True
         except Exception as e:
             self.logger.bind(tag=TAG).error(f"Chat and close error: {str(e)}")
+
+    async def _check_timeout(self):
+        """检查连接超时"""
+        try:
+            while not self.stop_event.is_set():
+                await asyncio.sleep(self.timeout_seconds)
+                if not self.stop_event.is_set():
+                    self.logger.bind(tag=TAG).info("连接超时，准备关闭")
+                    await self.close(self.websocket)
+                    break
+        except Exception as e:
+            self.logger.bind(tag=TAG).error(f"超时检查任务出错: {e}")

main/xiaozhi-server/core/handle/functionHandler.py

@@ -79,7 +79,7 @@ class FunctionHandler:
             func = funcItem.func
             arguments = function_call_data["arguments"]
             arguments = json.loads(arguments) if arguments else {}
-            logger.bind(tag=TAG).info(f"调用函数: {function_name}, 参数: {arguments}")
+            logger.bind(tag=TAG).debug(f"调用函数: {function_name}, 参数: {arguments}")
             if (
                 funcItem.type == ToolType.SYSTEM_CTL
                 or funcItem.type == ToolType.IOT_CTL

main/xiaozhi-server/core/handle/helloHandle.py

@@ -81,6 +81,8 @@ async def wakeupWordsResponse(conn):
     """唤醒词响应"""
     wakeup_word = random.choice(WAKEUP_CONFIG["words"])
     result = conn.llm.response_no_stream(conn.config["prompt"], wakeup_word)
+    if result is None or result == "":
+        return
     tts_file = await asyncio.to_thread(conn.tts.to_tts, result)
 
     if tts_file is not None and os.path.exists(tts_file):

main/xiaozhi-server/core/handle/iotHandle.py

@@ -57,7 +57,7 @@ def create_iot_function(device_name, method_name, method_info):
                 response_failure = "操作失败"
 
             # 打印响应参数
-            logger.bind(tag=TAG).info(
+            logger.bind(tag=TAG).debug(
                 f"控制函数接收到的响应参数: success='{response_success}', failure='{response_failure}'"
             )
 
@@ -144,33 +144,34 @@ class IotDescriptor:
         self.methods = []
 
         # 根据描述创建属性
-        for key, value in properties.items():
+        if properties is not None:
-            property_item = globals()[key] = {}
+            for key, value in properties.items():
-            property_item["name"] = key
+                property_item = {}
-            property_item["description"] = value["description"]
+                property_item["name"] = key
-            if value["type"] == "number":
+                property_item["description"] = value["description"]
-                property_item["value"] = 0
+                if value["type"] == "number":
-            elif value["type"] == "boolean":
+                    property_item["value"] = 0
-                property_item["value"] = False
+                elif value["type"] == "boolean":
-            else:
+                    property_item["value"] = False
-                property_item["value"] = ""
+                else:
-            self.properties.append(property_item)
+                    property_item["value"] = ""
+                self.properties.append(property_item)
 
         # 根据描述创建方法
-        for key, value in methods.items():
+        if methods is not None:
-            method = globals()[key] = {}
+            for key, value in methods.items():
-            method["description"] = value["description"]
+                method = {}
-            method["name"] = key
+                method["description"] = value["description"]
-            for k, v in value["parameters"].items():
+                method["name"] = key
-                method[k] = {}
+                # 检查方法是否有参数
-                method[k]["description"] = v["description"]
+                if "parameters" in value:
-                if v["type"] == "number":
+                    method["parameters"] = {}
-                    method[k]["value"] = 0
+                    for k, v in value["parameters"].items():
-                elif v["type"] == "boolean":
+                        method["parameters"][k] = {
-                    method[k]["value"] = False
+                            "description": v["description"],
-                else:
+                            "type": v["type"],
-                    method[k]["value"] = ""
+                        }
-            self.methods.append(method)
+                self.methods.append(method)
 
 
 def register_device_type(descriptor):
@@ -219,13 +220,19 @@ def register_device_type(descriptor):
         func_name = f"{device_name.lower()}_{method_name.lower()}"
 
         # 创建参数字典，添加原有参数
-        parameters = {
+        parameters = {}
-            param_name: {
+        required_params = []
-                "type": param_info["type"],
+
-                "description": param_info["description"],
+        # 如果方法有参数，则添加参数信息
+        if "parameters" in method_info:
+            parameters = {
+                param_name: {
+                    "type": param_info["type"],
+                    "description": param_info["description"],
+                }
+                for param_name, param_info in method_info["parameters"].items()
             }
-            for param_name, param_info in method_info["parameters"].items()
+            required_params = list(method_info["parameters"].keys())
-        }
 
         # 添加响应参数
         parameters.update(
@@ -242,7 +249,6 @@ def register_device_type(descriptor):
         )
 
         # 构建必须参数列表（原有参数 + 响应参数）
-        required_params = list(method_info["parameters"].keys())
         required_params.extend(["response_success", "response_failure"])
 
         func_desc = {
@@ -280,6 +286,25 @@ async def handleIotDescriptors(conn, descriptors):
     functions_changed = False
 
     for descriptor in descriptors:
+
+        # 如果descriptor没有properties和methods，则直接跳过
+        if "properties" not in descriptor and "methods" not in descriptor:
+            continue
+
+        # 处理缺失properties的情况
+        if "properties" not in descriptor:
+            descriptor["properties"] = {}
+            # 从methods中提取所有参数作为properties
+            if "methods" in descriptor:
+                for method_name, method_info in descriptor["methods"].items():
+                    if "parameters" in method_info:
+                        for param_name, param_info in method_info["parameters"].items():
+                            # 将参数信息转换为属性信息
+                            descriptor["properties"][param_name] = {
+                                "description": param_info["description"],
+                                "type": param_info["type"],
+                            }
+
         # 创建IOT设备描述符
         iot_descriptor = IotDescriptor(
             descriptor["name"],
@@ -373,19 +398,17 @@ async def send_iot_conn(conn, name, method_name, parameters):
             for method in value.methods:
                 # 找到了方法
                 if method["name"] == method_name:
-                    await conn.websocket.send(
+                    # 构建命令对象
-                        json.dumps(
+                    command = {
-                            {
+                        "name": name,
-                                "type": "iot",
+                        "method": method_name,
-                                "commands": [
+                    }
-                                    {
+
-                                        "name": name,
+                    # 只有当参数不为空时才添加parameters字段
-                                        "method": method_name,
+                    if parameters:
-                                        "parameters": parameters,
+                        command["parameters"] = parameters
-                                    }
+                    send_message = json.dumps({"type": "iot", "commands": [command]})
-                                ],
+                    await conn.websocket.send(send_message)
-                            }
+                    logger.bind(tag=TAG).info(f"发送物联网指令: {send_message}")
-                        )
-                    )
                     return
     logger.bind(tag=TAG).error(f"未找到方法{method_name}")

main/xiaozhi-server/core/handle/receiveAudioHandle.py

@@ -1,9 +1,9 @@
 from config.logger import setup_logging
 import time
-import asyncio
 from core.utils.util import remove_punctuation_and_length
 from core.handle.sendAudioHandle import send_stt_message
 from core.handle.intentHandler import handle_user_intent
+from core.utils.output_counter import check_device_output_limit
 
 TAG = __name__
 logger = setup_logging()
@@ -51,6 +51,15 @@ async def startToChat(conn, text):
     if conn.need_bind:
         await check_bind_device(conn)
         return
+
+    # 如果当日的输出字数大于限定的字数
+    if conn.max_output_size > 0:
+        if check_device_output_limit(
+            conn.headers.get("device-id"), conn.max_output_size
+        ):
+            await max_out_size(conn)
+            return
+
     # 首先进行意图分析
     intent_handled = await handle_user_intent(conn, text)
 
@@ -89,6 +98,18 @@ async def no_voice_close_connect(conn):
             await startToChat(conn, prompt)
 
 
+async def max_out_size(conn):
+    text = "不好意思，我现在有点事情要忙，明天这个时候我们再聊，约好了哦！明天不见不散，拜拜！"
+    await send_stt_message(conn, text)
+    conn.tts_first_text_index = 0
+    conn.tts_last_text_index = 0
+    conn.llm_finish_task = True
+    file_path = "config/assets/max_output_size.wav"
+    opus_packets, _ = conn.tts.audio_to_opus_data(file_path)
+    conn.audio_play_queue.put((opus_packets, text, 0))
+    conn.close_after_chat = True
+
+
 async def check_bind_device(conn):
     if conn.bind_code:
         # 确保bind_code是6位数字
@@ -115,7 +136,7 @@ async def check_bind_device(conn):
                 digit = conn.bind_code[i]
                 num_path = f"config/assets/bind_code/{digit}.wav"
                 num_packets, _ = conn.tts.audio_to_opus_data(num_path)
-                conn.audio_play_queue.put((num_packets, text, i + 1))
+                conn.audio_play_queue.put((num_packets, None, i + 1))
             except Exception as e:
                 logger.bind(tag=TAG).error(f"播放数字音频失败: {e}")
                 continue

main/xiaozhi-server/core/handle/sendAudioHandle.py

@@ -3,7 +3,6 @@ import json
 import asyncio
 import time
 from core.utils.util import (
-    remove_punctuation_and_length,
     get_string_no_punctuation_or_emoji,
 )
 

main/xiaozhi-server/core/providers/llm/base.py

@@ -35,4 +35,5 @@ class LLMProviderBase(ABC):
         """
         # For providers that don't support functions, just return regular response
         for token in self.response(session_id, dialogue):
-            yield {"type": "content", "content": token}
+            yield token, None
+

main/xiaozhi-server/core/providers/llm/coze/coze.py

@@ -4,9 +4,11 @@ import json
 import re
 from core.providers.llm.base import LLMProviderBase
 import os
+
 # official coze sdk for Python [cozepy](https://github.com/coze-dev/coze-py)
 from cozepy import COZE_CN_BASE_URL
 from cozepy import Coze, TokenAuth, Message, ChatStatus, MessageContentType, ChatEventType  # noqa
+from core.providers.llm.system_prompt import get_system_prompt_for_function
 
 TAG = __name__
 logger = setup_logging()
@@ -15,8 +17,8 @@ logger = setup_logging()
 class LLMProvider(LLMProviderBase):
     def __init__(self, config):
         self.personal_access_token = config.get("personal_access_token")
-        self.bot_id = config.get("bot_id")
+        self.bot_id = str(config.get("bot_id"))
-        self.user_id = config.get("user_id")
+        self.user_id = str(config.get("user_id"))
         self.session_conversation_map = {}  # 存储session_id和conversation_id的映射
 
     def response(self, session_id, dialogue):
@@ -24,16 +26,13 @@ class LLMProvider(LLMProviderBase):
         coze_api_base = COZE_CN_BASE_URL
 
         last_msg = next(m for m in reversed(dialogue) if m["role"] == "user")
-        
+
         coze = Coze(auth=TokenAuth(token=coze_api_token), base_url=coze_api_base)
         conversation_id = self.session_conversation_map.get(session_id)
 
         # 如果没有找到conversation_id，则创建新的对话
         if not conversation_id:
-            conversation = coze.conversations.create(
+            conversation = coze.conversations.create(messages=[])
-                messages=[
-                ]
-            )
             conversation_id = conversation.id
             self.session_conversation_map[session_id] = conversation_id  # 更新映射
 
@@ -47,4 +46,24 @@ class LLMProvider(LLMProviderBase):
         ):
             if event.event == ChatEventType.CONVERSATION_MESSAGE_DELTA:
                 print(event.message.content, end="", flush=True)
-                yield event.message.content
+                yield event.message.content
+
+    def response_with_functions(self, session_id, dialogue, functions=None):    
+        if len(dialogue) == 2 and functions is not None and len(functions) > 0:
+            # 第一次调用llm， 取最后一条用户消息，附加tool提示词
+            last_msg = dialogue[-1]["content"]
+            function_str = json.dumps(functions, ensure_ascii=False)
+            modify_msg = get_system_prompt_for_function(function_str) + last_msg
+            dialogue[-1]["content"] = modify_msg 
+
+        # 如果最后一个是 role="tool"，附加到user上
+        if len(dialogue) > 1 and dialogue[-1]["role"] == "tool":
+            assistant_msg = "\ntool call result: " + dialogue[-1]["content"] + "\n\n"
+            while len(dialogue) > 1 :
+                if dialogue[-1]["role"] == "user":
+                    dialogue[-1]["content"] = assistant_msg + dialogue[-1]["content"]
+                    break
+                dialogue.pop()
+        
+        for token in self.response(session_id, dialogue):
+            yield token, None

main/xiaozhi-server/core/providers/llm/dify/dify.py

@@ -2,6 +2,7 @@ import json
 from config.logger import setup_logging
 import requests
 from core.providers.llm.base import LLMProviderBase
+from core.providers.llm.system_prompt import get_system_prompt_for_function
 
 TAG = __name__
 logger = setup_logging()
@@ -81,3 +82,23 @@ class LLMProvider(LLMProviderBase):
         except Exception as e:
             logger.bind(tag=TAG).error(f"Error in response generation: {e}")
             yield "【服务响应异常】"
+
+    def response_with_functions(self, session_id, dialogue, functions=None):    
+        if len(dialogue) == 2 and functions is not None and len(functions) > 0:
+            # 第一次调用llm， 取最后一条用户消息，附加tool提示词
+            last_msg = dialogue[-1]["content"]
+            function_str = json.dumps(functions, ensure_ascii=False)
+            modify_msg = get_system_prompt_for_function(function_str) + last_msg
+            dialogue[-1]["content"] = modify_msg 
+
+        # 如果最后一个是 role="tool"，附加到user上
+        if len(dialogue) > 1 and dialogue[-1]["role"] == "tool":
+            assistant_msg = "\ntool call result: " + dialogue[-1]["content"] + "\n\n"
+            while len(dialogue) > 1 :
+                if dialogue[-1]["role"] == "user":
+                    dialogue[-1]["content"] = assistant_msg + dialogue[-1]["content"]
+                    break
+                dialogue.pop()
+        
+        for token in self.response(session_id, dialogue):
+            yield token, None

main/xiaozhi-server/core/providers/llm/ollama/ollama.py

@@ -63,4 +63,4 @@ class LLMProvider(LLMProviderBase):
 
         except Exception as e:
             logger.bind(tag=TAG).error(f"Error in Ollama function call: {e}")
-            yield {"type": "content", "content": f"【Ollama服务响应异常: {str(e)}】"}
+            yield f"【Ollama服务响应异常: {str(e)}】", None

main/xiaozhi-server/core/providers/llm/openai/openai.py

@@ -74,4 +74,4 @@ class LLMProvider(LLMProviderBase):
 
         except Exception as e:
             logger.bind(tag=TAG).error(f"Error in function call streaming: {e}")
-            yield {"type": "content", "content": f"【OpenAI服务响应异常: {e}】"}
+            yield f"【OpenAI服务响应异常: {e}】", None

main/xiaozhi-server/core/providers/llm/system_prompt.py

@@ -0,0 +1,103 @@
+def get_system_prompt_for_function(functions: str) -> str:
+    """
+    生成系统提示信息
+    :param functions: 可用的函数列表
+    :return: 系统提示信息
+    """
+
+    SYSTEM_PROMPT = f"""
+====
+
+TOOL USE
+
+You have access to a set of tools that are executed upon the user's approval. You can use one tool per message, and will receive the result of that tool use in the user's response. 
+You use tools step-by-step to accomplish a given task, with each tool use informed by the result of the previous tool use.
+
+# Tool Use Formatting
+
+Tool use is formatted using JSON-style tags. The tool name is enclosed in opening and closing tags, and each parameter is similarly enclosed within its own set of tags. 
+Here's the structure:
+
+<tool_call>
+{{
+    "name": "function name",
+    "arguments": {{
+        "param1": "value1",
+        "param2": "value2",
+        // Add more parameters as needed, if parameters are required, you must provide them
+    }}
+}}
+<tool_call>
+
+For example:
+if you got tool as follow
+
+{{
+    "type": "function",
+    "function": {{
+        "name": "handle_exit_intent",
+        "description": "当用户想结束对话或需要退出系统时调用",
+        "parameters": {{
+            "type": "object",
+            "properties": {{
+                "say_goodbye": {{
+                    "type": "string",
+                    "description": "和用户友好结束对话的告别语",
+                }}
+            }},
+            "required": ["say_goodbye"],
+        }},
+    }},
+}}
+
+you should respond with the following format:
+
+<tool_call>
+{{
+    "name": "handle_exit_intent",
+    "arguments": {{
+        "say_goodbye": "再见，祝您生活愉快！"
+    }}
+}}
+</tool_call>
+
+
+Always adhere to this format for the tool use to ensure proper parsing and execution.
+
+# Tools
+
+{functions}
+
+# Tool Use Guidelines
+
+1. Tools must be called in a separate message, Do not add thoughts when calling tools. The message must start with <tool_call> and end with </tool_call>, with the tool invocation JSON data in between. No additional response content is needed.
+2. Choose the most appropriate tool based on the task and the tool descriptions provided. Assess if you need additional information to proceed, and which of the available tools would be most effective for gathering this information. 
+   For example using the list_files tool is more effective than running a command like \`ls\` in the terminal. It's critical that you think about each available tool and use the one that best fits the current step in the task.
+3. If multiple actions are needed, use one tool at a time per message to accomplish the task iteratively, with each tool use being informed by the result of the previous tool use. Do not assume the outcome of any tool use. 
+   Each step must be informed by the previous step's result.
+4. Formulate your tool use using the JSON format specified for each tool.
+5. After each tool use, the user will respond with the result of that tool use. This result will provide you with the necessary information to continue your task or make further decisions. This response may include:
+- Information about whether the tool succeeded or failed, along with any reasons for failure.
+- Linter errors that may have arisen due to the changes you made, which you'll need to address.
+- New terminal output in reaction to the changes, which you may need to consider or act upon.
+- Any other relevant feedback or information related to the tool use.
+6. ALWAYS wait for user confirmation after each tool use before proceeding. Never assume the success of a tool use without explicit confirmation of the result from the user.
+7. Tool calls should contain no extra information. Only after receiving the tool's response should you integrate it into a complete reply.
+
+It is crucial to proceed step-by-step, waiting for the user's message after each tool use before moving forward with the task. This approach allows you to:
+1. Confirm the success of each step before proceeding.
+2. Address any issues or errors that arise immediately.
+3. Adapt your approach based on new information or unexpected results.
+4. Ensure that each action builds correctly on the previous ones.
+
+By waiting for and carefully considering the user's response after each tool use, you can react accordingly and make informed decisions about how to proceed with the task. This iterative process helps ensure the overall success and accuracy of your work.
+
+====
+
+USER CHAT CONTENT
+
+The following additional message is the user's chat message, and should be followed to the best of your ability without interfering with the TOOL USE guidelines.
+
+"""
+
+    return SYSTEM_PROMPT

main/xiaozhi-server/core/providers/tts/fishspeech.py

@@ -8,7 +8,7 @@ from pydantic import BaseModel, Field, conint, model_validator
 from typing_extensions import Annotated
 from datetime import datetime
 from typing import Literal
-from core.utils.util import check_model_key
+from core.utils.util import check_model_key, parse_string_to_list
 from core.providers.tts.base import TTSProviderBase
 from config.logger import setup_logging
 
@@ -86,8 +86,8 @@ class TTSProvider(TTSProviderBase):
         super().__init__(config, delete_audio_file)
 
         self.reference_id = config.get("reference_id")
-        self.reference_audio = config.get("reference_audio", [])
+        self.reference_audio = parse_string_to_list(config.get("reference_audio"))
-        self.reference_text = config.get("reference_text", [])
+        self.reference_text = parse_string_to_list(config.get("reference_text"))
         self.format = config.get("format", "wav")
         self.channels = int(config.get("channels", 1))
         self.rate = int(config.get("rate", 44100))
@@ -101,9 +101,13 @@ class TTSProvider(TTSProviderBase):
         self.top_p = float(config.get("top_p", 0.7))
         self.repetition_penalty = float(config.get("repetition_penalty", 1.2))
         self.temperature = float(config.get("temperature", 0.7))
-        self.streaming = bool(config.get("streaming", False))
+        self.streaming = str(config.get("streaming", False)).lower() in (
+            "true",
+            "1",
+            "yes",
+        )
         self.use_memory_cache = config.get("use_memory_cache", "on")
-        self.seed = config.get("seed")
+        self.seed = config.get("seed") or None
         self.api_url = config.get("api_url", "http://127.0.0.1:8080/v1/tts")
 
     def generate_filename(self, extension=".wav"):

main/xiaozhi-server/core/providers/tts/gpt_sovits_v2.py

@@ -6,6 +6,7 @@ import requests
 from config.logger import setup_logging
 from datetime import datetime
 from core.providers.tts.base import TTSProviderBase
+from core.utils.util import parse_string_to_list
 
 TAG = __name__
 logger = setup_logging()
@@ -25,14 +26,33 @@ class TTSProvider(TTSProviderBase):
         self.text_split_method = config.get("text_split_method", "cut0")
         self.batch_size = int(config.get("batch_size", 1))
         self.batch_threshold = float(config.get("batch_threshold", 0.75))
-        self.split_bucket = bool(config.get("split_bucket", True))
+
-        self.return_fragment = bool(config.get("return_fragment", False))
+        self.split_bucket = str(config.get("split_bucket", True)).lower() in (
+            "true",
+            "1",
+            "yes",
+        )
+        self.return_fragment = str(config.get("return_fragment", False)).lower() in (
+            "true",
+            "1",
+            "yes",
+        )
         self.speed_factor = float(config.get("speed_factor", 1.0))
-        self.streaming_mode = bool(config.get("streaming_mode", False))
+        self.streaming_mode = str(config.get("streaming_mode", False)).lower() in (
+            "true",
+            "1",
+            "yes",
+        )
         self.seed = int(config.get("seed", -1))
-        self.parallel_infer = bool(config.get("parallel_infer", True))
+        self.parallel_infer = str(config.get("parallel_infer", True)).lower() in (
+            "true",
+            "1",
+            "yes",
+        )
         self.repetition_penalty = float(config.get("repetition_penalty", 1.35))
-        self.aux_ref_audio_paths = config.get("aux_ref_audio_paths", [])
+        self.aux_ref_audio_paths = parse_string_to_list(
+            config.get("aux_ref_audio_paths")
+        )
 
     def generate_filename(self, extension=".wav"):
         return os.path.join(

main/xiaozhi-server/core/providers/tts/gpt_sovits_v3.py

@@ -4,6 +4,7 @@ import requests
 from config.logger import setup_logging
 from datetime import datetime
 from core.providers.tts.base import TTSProviderBase
+from core.utils.util import parse_string_to_list
 
 TAG = __name__
 logger = setup_logging()
@@ -22,9 +23,9 @@ class TTSProvider(TTSProviderBase):
         self.temperature = float(config.get("temperature", 1.0))
         self.cut_punc = config.get("cut_punc", "")
         self.speed = float(config.get("speed", 1.0))
-        self.inp_refs = config.get("inp_refs", [])
+        self.inp_refs = parse_string_to_list(config.get("inp_refs"))
         self.sample_steps = int(config.get("sample_steps", 32))
-        self.if_sr = bool(config.get("if_sr", False))
+        self.if_sr = str(config.get("if_sr", False)).lower() in ("true", "1", "yes")
 
     def generate_filename(self, extension=".wav"):
         return os.path.join(

main/xiaozhi-server/core/providers/tts/minimax.py

@@ -4,6 +4,7 @@ import json
 import requests
 from datetime import datetime
 from core.providers.tts.base import TTSProviderBase
+from core.utils.util import parse_string_to_list
 
 
 class TTSProvider(TTSProviderBase):
@@ -40,7 +41,7 @@ class TTSProvider(TTSProviderBase):
             **config.get("pronunciation_dict", {}),
         }
         self.audio_setting = {**defult_audio_setting, **config.get("audio_setting", {})}
-        self.timber_weights = config.get("timber_weights", [])
+        self.timber_weights = parse_string_to_list(config.get("timber_weights"))
 
         if self.voice_id:
             self.voice_setting["voice_id"] = self.voice_id

main/xiaozhi-server/core/providers/tts/ttson.py

@@ -22,7 +22,7 @@ class TTSProvider(TTSProviderBase):
         self.to_lang = config.get("to_lang")
         self.volume_change_dB = int(config.get("volume_change_dB", 0))
         self.speed_factor = int(config.get("speed_factor", 1))
-        self.stream = bool(config.get("stream", False))
+        self.stream = str(config.get("stream", False)).lower() in ("true", "1", "yes")
         self.output_file = config.get("output_dir")
         self.pitch_factor = int(config.get("pitch_factor", 0))
         self.format = config.get("format", "mp3")

main/xiaozhi-server/core/utils/output_counter.py

@@ -0,0 +1,50 @@
+import datetime
+from typing import Dict, Tuple
+
+# 全局字典，用于存储每个设备的每日输出字数
+_device_daily_output: Dict[Tuple[str, datetime.date], int] = {}
+# 记录最后一次检查的日期
+_last_check_date: datetime.date = None
+
+
+def reset_device_output():
+    """
+    重置所有设备的每日输出字数
+    每天0点调用此函数
+    """
+    _device_daily_output.clear()
+
+
+def get_device_output(device_id: str) -> int:
+    """
+    获取设备当日的输出字数
+    """
+    current_date = datetime.datetime.now().date()
+    return _device_daily_output.get((device_id, current_date), 0)
+
+
+def add_device_output(device_id: str, char_count: int):
+    """
+    增加设备的输出字数
+    """
+    current_date = datetime.datetime.now().date()
+    global _last_check_date
+
+    # 如果是第一次调用或者日期发生变化，清空计数器
+    if _last_check_date is None or _last_check_date != current_date:
+        _device_daily_output.clear()
+        _last_check_date = current_date
+
+    current_count = _device_daily_output.get((device_id, current_date), 0)
+    _device_daily_output[(device_id, current_date)] = current_count + char_count
+
+
+def check_device_output_limit(device_id: str, max_output_size: int) -> bool:
+    """
+    检查设备是否超过输出限制
+    :return: True 如果超过限制，False 如果未超过
+    """
+    if not device_id:
+        return False
+    current_output = get_device_output(device_id)
+    return current_output >= max_output_size

main/xiaozhi-server/core/utils/util.py

@@ -163,6 +163,24 @@ def check_model_key(modelType, modelKey):
     return True
 
 
+def parse_string_to_list(value, separator=";"):
+    """
+    将输入值转换为列表
+    Args:
+        value: 输入值，可以是 None、字符串或列表
+        separator: 分隔符，默认为分号
+    Returns:
+        list: 处理后的列表
+    """
+    if value is None or value == "":
+        return []
+    elif isinstance(value, str):
+        return [item.strip() for item in value.split(separator) if item.strip()]
+    elif isinstance(value, list):
+        return value
+    return []
+
+
 def check_ffmpeg_installed():
     ffmpeg_installed = False
     try:
@@ -193,7 +211,7 @@ def check_ffmpeg_installed():
 def extract_json_from_string(input_string):
     """提取字符串中的 JSON 部分"""
     pattern = r"(\{.*\})"
-    match = re.search(pattern, input_string)
+    match = re.search(pattern, input_string, re.DOTALL)  #添加 re.DOTALL
     if match:
         return match.group(1)  # 返回提取的 JSON 字符串
     return None
@@ -231,7 +249,7 @@ def initialize_modules(
         modules["tts"] = tts.create_instance(
             tts_type,
             config["TTS"][select_tts_module],
-            bool(config.get("delete_audio", True)),
+            str(config.get("delete_audio", True)).lower() in ("true", "1", "yes"),
         )
         logger.bind(tag=TAG).info(f"初始化组件: tts成功 {select_tts_module}")
 
@@ -302,7 +320,7 @@ def initialize_modules(
         modules["asr"] = asr.create_instance(
             asr_type,
             config["ASR"][select_asr_module],
-            bool(config.get("delete_audio", True)),
+            str(config.get("delete_audio", True)).lower() in ("true", "1", "yes"),
         )
         logger.bind(tag=TAG).info(f"初始化组件: asr成功 {select_asr_module}")
 

main/xiaozhi-server/docker-compose_all.yml

@@ -42,7 +42,6 @@ services:
       - "8002:8002"
     environment:
       - TZ=Asia/Shanghai
-      ##记得改mysql和redis IP 密码
       - SPRING_DATASOURCE_DRUID_URL=jdbc:mysql://xiaozhi-esp32-server-db:3306/xiaozhi_esp32_server?useUnicode=true&characterEncoding=UTF-8&serverTimezone=Asia/Shanghai&nullCatalogMeansCurrent=true&connectTimeout=30000&socketTimeout=30000&autoReconnect=true&failOverReadOnly=false&maxReconnects=10
       - SPRING_DATASOURCE_DRUID_USERNAME=root
       - SPRING_DATASOURCE_DRUID_PASSWORD=123456

main/xiaozhi-server/plugins_func/functions/play_music.py

@@ -9,7 +9,7 @@ import traceback
 from pathlib import Path
 from core.utils import p3
 from core.handle.sendAudioHandle import send_stt_message
-from plugins_func.register import register_function,ToolType, ActionResponse, Action
+from plugins_func.register import register_function, ToolType, ActionResponse, Action
 
 
 TAG = __name__
@@ -18,38 +18,41 @@ logger = setup_logging()
 MUSIC_CACHE = {}
 
 play_music_function_desc = {
-                "type": "function",
+    "type": "function",
-                "function": {
+    "function": {
-                    "name": "play_music",
+        "name": "play_music",
-                    "description": "唱歌、听歌、播放音乐的方法。",
+        "description": "唱歌、听歌、播放音乐的方法。",
-                    "parameters": {
+        "parameters": {
-                        "type": "object",
+            "type": "object",
-                        "properties": {
+            "properties": {
-                            "song_name": {
+                "song_name": {
-                                "type": "string",
+                    "type": "string",
-                                "description": "歌曲名称，如果用户没有指定具体歌名则为'random', 明确指定的时返回音乐的名字 示例: ```用户:播放两只老虎\n参数：两只老虎``` ```用户:播放音乐 \n参数：random ```"
+                    "description": "歌曲名称，如果用户没有指定具体歌名则为'random', 明确指定的时返回音乐的名字 示例: ```用户:播放两只老虎\n参数：两只老虎``` ```用户:播放音乐 \n参数：random ```",
-                            }
-                        },
-                        "required": ["song_name"]
-                    }
                 }
-            }
+            },
+            "required": ["song_name"],
+        },
+    },
+}
 
 
-@register_function('play_music', play_music_function_desc, ToolType.SYSTEM_CTL)
+@register_function("play_music", play_music_function_desc, ToolType.SYSTEM_CTL)
 def play_music(conn, song_name: str):
     try:
-        music_intent = f"播放音乐 {song_name}" if song_name != "random" else "随机播放音乐"
+        music_intent = (
+            f"播放音乐 {song_name}" if song_name != "random" else "随机播放音乐"
+        )
 
         # 检查事件循环状态
         if not conn.loop.is_running():
             logger.bind(tag=TAG).error("事件循环未运行，无法提交任务")
-            return ActionResponse(action=Action.RESPONSE, result="系统繁忙", response="请稍后再试")
+            return ActionResponse(
+                action=Action.RESPONSE, result="系统繁忙", response="请稍后再试"
+            )
 
         # 提交异步任务
         future = asyncio.run_coroutine_threadsafe(
-            handle_music_command(conn, music_intent),
+            handle_music_command(conn, music_intent), conn.loop
-            conn.loop
         )
 
         # 非阻塞回调处理
@@ -62,10 +65,14 @@ def play_music(conn, song_name: str):
 
         future.add_done_callback(handle_done)
 
-        return ActionResponse(action=Action.RESPONSE, result="指令已接收", response="正在为您播放音乐")
+        return ActionResponse(
+            action=Action.NONE, result="指令已接收", response="正在为您播放音乐"
+        )
     except Exception as e:
         logger.bind(tag=TAG).error(f"处理音乐意图错误: {e}")
-        return ActionResponse(action=Action.RESPONSE, result=str(e), response="播放音乐时出错了")
+        return ActionResponse(
+            action=Action.RESPONSE, result=str(e), response="播放音乐时出错了"
+        )
 
 
 def _extract_song_name(text):
@@ -105,7 +112,9 @@ def get_music_files(music_dir, music_ext):
             if ext in music_ext:
                 # 添加相对路径
                 music_files.append(str(file.relative_to(music_dir)))
-                music_file_names.append(os.path.splitext(str(file.relative_to(music_dir)))[0])
+                music_file_names.append(
+                    os.path.splitext(str(file.relative_to(music_dir)))[0]
+                )
     return music_files, music_file_names
 
 
@@ -117,15 +126,20 @@ def initialize_music_handler(conn):
             MUSIC_CACHE["music_dir"] = os.path.abspath(
                 MUSIC_CACHE["music_config"].get("music_dir", "./music")  # 默认路径修改
             )
-            MUSIC_CACHE["music_ext"] = MUSIC_CACHE["music_config"].get("music_ext", (".mp3", ".wav", ".p3"))
+            MUSIC_CACHE["music_ext"] = MUSIC_CACHE["music_config"].get(
-            MUSIC_CACHE["refresh_time"] = MUSIC_CACHE["music_config"].get("refresh_time", 60)
+                "music_ext", (".mp3", ".wav", ".p3")
+            )
+            MUSIC_CACHE["refresh_time"] = MUSIC_CACHE["music_config"].get(
+                "refresh_time", 60
+            )
         else:
             MUSIC_CACHE["music_dir"] = os.path.abspath("./music")
             MUSIC_CACHE["music_ext"] = (".mp3", ".wav", ".p3")
             MUSIC_CACHE["refresh_time"] = 60
         # 获取音乐文件列表
-        MUSIC_CACHE["music_files"], MUSIC_CACHE["music_file_names"] = get_music_files(MUSIC_CACHE["music_dir"],
+        MUSIC_CACHE["music_files"], MUSIC_CACHE["music_file_names"] = get_music_files(
-                                                                                      MUSIC_CACHE["music_ext"])
+            MUSIC_CACHE["music_dir"], MUSIC_CACHE["music_ext"]
+        )
         MUSIC_CACHE["scan_time"] = time.time()
     return MUSIC_CACHE
 
@@ -135,15 +149,16 @@ async def handle_music_command(conn, text):
     global MUSIC_CACHE
 
     """处理音乐播放指令"""
-    clean_text = re.sub(r'[^\w\s]', '', text).strip()
+    clean_text = re.sub(r"[^\w\s]", "", text).strip()
     logger.bind(tag=TAG).debug(f"检查是否是音乐命令: {clean_text}")
 
     # 尝试匹配具体歌名
     if os.path.exists(MUSIC_CACHE["music_dir"]):
         if time.time() - MUSIC_CACHE["scan_time"] > MUSIC_CACHE["refresh_time"]:
             # 刷新音乐文件列表
-            MUSIC_CACHE["music_files"], MUSIC_CACHE["music_file_names"] = get_music_files(MUSIC_CACHE["music_dir"],
+            MUSIC_CACHE["music_files"], MUSIC_CACHE["music_file_names"] = (
-                                                                                          MUSIC_CACHE["music_ext"])
+                get_music_files(MUSIC_CACHE["music_dir"], MUSIC_CACHE["music_ext"])
+            )
             MUSIC_CACHE["scan_time"] = time.time()
 
         potential_song = _extract_song_name(clean_text)
@@ -158,6 +173,23 @@ async def handle_music_command(conn, text):
     return True
 
 
+def _get_random_play_prompt(song_name):
+    """生成随机播放引导语"""
+    # 移除文件扩展名
+    clean_name = os.path.splitext(song_name)[0]
+    prompts = [
+        f"正在为您播放，{clean_name}",
+        f"请欣赏歌曲，{clean_name}",
+        f"即将为您播放，{clean_name}",
+        f"为您带来，{clean_name}",
+        f"让我们聆听，{clean_name}",
+        f"接下来请欣赏，{clean_name}",
+        f"为您献上，{clean_name}",
+    ]
+    # 直接使用random.choice，不设置seed
+    return random.choice(prompts)
+
+
 async def play_local_music(conn, specific_file=None):
     global MUSIC_CACHE
     """播放本地音乐文件"""
@@ -180,16 +212,25 @@ async def play_local_music(conn, specific_file=None):
         if not os.path.exists(music_path):
             logger.bind(tag=TAG).error(f"选定的音乐文件不存在: {music_path}")
             return
-        text = f"正在播放{selected_music}"
+        text = _get_random_play_prompt(selected_music)
         await send_stt_message(conn, text)
         conn.tts_first_text_index = 0
         conn.tts_last_text_index = 0
+
+        tts_file = await asyncio.to_thread(conn.tts.to_tts, text)
+        if tts_file is not None and os.path.exists(tts_file):
+            conn.tts_last_text_index = 1
+            opus_packets, _ = conn.tts.audio_to_opus_data(tts_file)
+            conn.audio_play_queue.put((opus_packets, None, 0))
+            os.remove(tts_file)
+
         conn.llm_finish_task = True
+
         if music_path.endswith(".p3"):
-            opus_packets, duration = p3.decode_opus_from_file(music_path)
+            opus_packets, _ = p3.decode_opus_from_file(music_path)
         else:
-            opus_packets, duration = conn.tts.audio_to_opus_data(music_path)
+            opus_packets, _ = conn.tts.audio_to_opus_data(music_path)
-        conn.audio_play_queue.put((opus_packets, selected_music, 0))
+        conn.audio_play_queue.put((opus_packets, None, conn.tts_last_text_index))
 
     except Exception as e:
         logger.bind(tag=TAG).error(f"播放音乐失败: {str(e)}")

main/xiaozhi-server/test/test_page.html

@@ -42,6 +42,50 @@
             display: flex;
             align-items: center;
             gap: 10px;
+            padding: 10px 0;
+        }
+
+        .section h2 .toggle-button {
+            margin-left: auto;
+            padding: 4px 12px;
+            font-size: 12px;
+            border-radius: 4px;
+            cursor: pointer;
+            height: 28px;
+            line-height: 20px;
+        }
+
+        .device-info {
+            display: flex;
+            align-items: center;
+            gap: 20px;
+            margin-left: 20px;
+            padding: 0 15px;
+            background-color: #f9f9f9;
+            border-radius: 4px;
+            height: 28px;
+            line-height: 28px;
+        }
+
+        .device-info span {
+            color: #666;
+            font-size: 13px;
+        }
+
+        .device-info strong {
+            color: #333;
+            font-weight: 500;
+        }
+
+        .config-panel {
+            display: none;
+            transition: all 0.3s ease;
+            margin-top: 5px;
+            padding: 5px 0;
+        }
+
+        .config-panel.expanded {
+            display: block;
         }
 
         .control-panel {
@@ -70,7 +114,8 @@
             cursor: not-allowed;
         }
 
-        #serverUrl {
+        #serverUrl,
+        #otaUrl {
             flex-grow: 1;
             padding: 8px;
             border: 1px solid #ddd;
@@ -316,6 +361,76 @@
             gap: 20px;
             margin-top: 10px;
         }
+
+        .config-item {
+            display: flex;
+            align-items: center;
+            margin-bottom: 8px;
+            width: 100%;
+        }
+
+        .config-item label {
+            width: 100px;
+            text-align: right;
+            margin-right: 10px;
+            color: #666;
+        }
+
+        .config-item input {
+            flex-grow: 1;
+            padding: 6px;
+            border: 1px solid #ddd;
+            border-radius: 5px;
+        }
+
+        .control-panel {
+            display: flex;
+            flex-direction: column;
+            gap: 10px;
+            margin-top: 10px;
+        }
+
+        .connection-controls {
+            display: flex;
+            gap: 10px;
+            align-items: center;
+            width: 100%;
+        }
+
+        .connection-controls input {
+            flex: 1;
+            padding: 8px;
+            border: 1px solid #ddd;
+            border-radius: 5px;
+            min-width: 200px;
+        }
+
+        .connection-controls button {
+            white-space: nowrap;
+            padding: 8px 15px;
+        }
+
+        .connection-status {
+            display: flex;
+            align-items: center;
+            gap: 20px;
+            margin-left: 20px;
+            padding: 0 15px;
+            background-color: #f9f9f9;
+            border-radius: 4px;
+            height: 28px;
+            line-height: 28px;
+        }
+
+        .connection-status span {
+            color: #666;
+            font-size: 13px;
+        }
+
+        .connection-status .status {
+            color: #333;
+            font-weight: 500;
+        }
     </style>
 </head>
 
@@ -326,17 +441,56 @@
         <div id="scriptStatus" style="position: fixed; top: 50%; left: 50%; transform: translate(-50%, -50%);">
             正在加载Opus库...</div>
 
+        <!-- 添加配置面板 -->
         <div class="section">
-            <h2>WebSocket连接 <span id="connectionStatus" class="status">未连接</span></h2>
+            <h2>
-            <div class="control-panel">
+                设备配置
-                <input type="text" id="serverUrl" value="ws://127.0.0.1:8000/xiaozhi/v1/" placeholder="WebSocket服务器地址">
+                <span class="device-info">
+                    <span>MAC: <strong id="displayMac">00:11:22:33:44:55</strong></span>
+                    <span>客户端: <strong id="displayClient">web_test_client</strong></span>
+                </span>
+                <button class="toggle-button" id="toggleConfig">编辑</button>
+            </h2>
+            <div class="config-panel" id="configPanel">
+                <div class="control-panel">
+                    <div class="config-item">
+                        <label for="deviceMac">设备MAC:</label>
+                        <input type="text" id="deviceMac" value="00:11:22:33:44:55" placeholder="设备MAC地址">
+                    </div>
+                    <div class="config-item">
+                        <label for="deviceName">设备名称:</label>
+                        <input type="text" id="deviceName" value="Web测试设备" placeholder="设备名称">
+                    </div>
+                    <div class="config-item">
+                        <label for="clientId">客户端ID:</label>
+                        <input type="text" id="clientId" value="web_test_client" placeholder="客户端ID">
+                    </div>
+                    <div class="config-item">
+                        <label for="token">认证Token:</label>
+                        <input type="text" id="token" value="your-token1" placeholder="认证Token">
+                    </div>
+                </div>
+            </div>
+        </div>
+
+        <div class="section">
+            <h2>
+                连接信息
+                <span class="connection-status">
+                    <span>OTA: <span id="otaStatus" class="status">ota未连接</span></span>
+                    <span>WS: <span id="connectionStatus" class="status">ws未连接</span></span>
+                </span>
+            </h2>
+            <div class="connection-controls">
+                <input type="text" id="otaUrl" value="http://127.0.0.1:8002/xiaozhi/ota/" placeholder="OTA服务器地址" />
+                <input type="text" id="serverUrl" value="ws://127.0.0.1:8000/xiaozhi/v1/"
+                    placeholder="WebSocket服务器地址" />
                 <button id="connectButton">连接</button>
                 <button id="authTestButton">测试认证</button>
             </div>
         </div>
 
         <div class="section">
-            <h2>消息发送</h2>
             <div class="tabs">
                 <button class="tab active" data-tab="text">文本消息</button>
                 <button class="tab" data-tab="voice">语音消息</button>
@@ -554,16 +708,16 @@
         // 开始音频缓冲过程
         function startAudioBuffering() {
             if (isAudioBuffering || isAudioPlaying) return;
-            
+
             isAudioBuffering = true;
             log("开始音频缓冲...", 'info');
-            
+
             // 先尝试初始化解码器，以便在播放时已准备好
             initOpusDecoder().catch(error => {
                 log(`预初始化Opus解码器失败: ${error.message}`, 'warning');
                 // 继续缓冲，我们会在播放时再次尝试初始化
             });
-            
+
             // 设置超时，如果在一定时间内没有收集到足够的音频包，就开始播放
             setTimeout(() => {
                 if (isAudioBuffering && audioBufferQueue.length > 0) {
@@ -571,14 +725,14 @@
                     playBufferedAudio();
                 }
             }, 300); // 300ms超时
-            
+
             // 监控缓冲进度
             const bufferCheckInterval = setInterval(() => {
                 if (!isAudioBuffering) {
                     clearInterval(bufferCheckInterval);
                     return;
                 }
-                
+
                 // 当累积了足够的音频包，开始播放
                 if (audioBufferQueue.length >= BUFFER_THRESHOLD) {
                     clearInterval(bufferCheckInterval);
@@ -591,10 +745,10 @@
         // 播放已缓冲的音频
         function playBufferedAudio() {
             if (isAudioPlaying || audioBufferQueue.length === 0) return;
-            
+
             isAudioPlaying = true;
             isAudioBuffering = false;
-            
+
             // 确保Opus解码器已初始化
             const initDecoderAndPlay = async () => {
                 try {
@@ -605,7 +759,7 @@
                         });
                         log('创建音频上下文，采样率: ' + SAMPLE_RATE + 'Hz', 'debug');
                     }
-                    
+
                     // 确保解码器已初始化
                     if (!opusDecoder) {
                         log('初始化Opus解码器...', 'info');
@@ -621,7 +775,7 @@
                             return;
                         }
                     }
-                    
+
                     // 创建流式播放上下文
                     if (!streamingContext) {
                         streamingContext = {
@@ -631,16 +785,16 @@
                             source: null,       // 当前音频源
                             totalSamples: 0,    // 累积的总样本数
                             lastPlayTime: 0,    // 上次播放的时间戳
-                            
+
                             // 将Opus数据解码为PCM
-                            decodeOpusFrames: async function(opusFrames) {
+                            decodeOpusFrames: async function (opusFrames) {
                                 if (!opusDecoder) {
                                     log('Opus解码器未初始化，无法解码', 'error');
                                     return;
                                 }
-                                
+
                                 let decodedSamples = [];
-                                
+
                                 for (const frame of opusFrames) {
                                     try {
                                         // 使用Opus解码器解码
@@ -654,12 +808,12 @@
                                         log("Opus解码失败: " + error.message, 'error');
                                     }
                                 }
-                                
+
                                 if (decodedSamples.length > 0) {
                                     // 添加到解码队列
                                     this.queue.push(...decodedSamples);
                                     this.totalSamples += decodedSamples.length;
-                                    
+
                                     // 如果累积了至少0.2秒的音频，开始播放
                                     const minSamples = SAMPLE_RATE * MIN_AUDIO_DURATION;
                                     if (!this.playing && this.queue.length >= minSamples) {
@@ -669,50 +823,50 @@
                                     log('没有成功解码的样本', 'warning');
                                 }
                             },
-                            
+
                             // 开始播放音频
-                            startPlaying: function() {
+                            startPlaying: function () {
                                 if (this.playing || this.queue.length === 0) return;
-                                
+
                                 this.playing = true;
-                                
+
                                 // 创建新的音频缓冲区
                                 const minPlaySamples = Math.min(this.queue.length, SAMPLE_RATE); // 最多播放1秒
                                 const currentSamples = this.queue.splice(0, minPlaySamples);
-                                
+
                                 const audioBuffer = audioContext.createBuffer(CHANNELS, currentSamples.length, SAMPLE_RATE);
                                 audioBuffer.copyToChannel(new Float32Array(currentSamples), 0);
-                                
+
                                 // 创建音频源
                                 this.source = audioContext.createBufferSource();
                                 this.source.buffer = audioBuffer;
-                                
+
                                 // 创建增益节点用于平滑过渡
                                 const gainNode = audioContext.createGain();
-                                
+
                                 // 应用淡入淡出效果避免爆音
                                 const fadeDuration = 0.02; // 20毫秒
                                 gainNode.gain.setValueAtTime(0, audioContext.currentTime);
                                 gainNode.gain.linearRampToValueAtTime(1, audioContext.currentTime + fadeDuration);
-                                
+
                                 const duration = audioBuffer.duration;
                                 if (duration > fadeDuration * 2) {
                                     gainNode.gain.setValueAtTime(1, audioContext.currentTime + duration - fadeDuration);
                                     gainNode.gain.linearRampToValueAtTime(0, audioContext.currentTime + duration);
                                 }
-                                
+
                                 // 连接节点并开始播放
                                 this.source.connect(gainNode);
                                 gainNode.connect(audioContext.destination);
-                                
+
                                 this.lastPlayTime = audioContext.currentTime;
                                 log(`开始播放 ${currentSamples.length} 个样本，约 ${(currentSamples.length / SAMPLE_RATE).toFixed(2)} 秒`, 'info');
-                                
+
                                 // 播放结束后的处理
                                 this.source.onended = () => {
                                     this.source = null;
                                     this.playing = false;
-                                    
+
                                     // 如果队列中还有数据或者缓冲区有新数据，继续播放
                                     if (this.queue.length > 0) {
                                         setTimeout(() => this.startPlaying(), 10);
@@ -743,26 +897,26 @@
                                         }, 500); // 500ms超时
                                     }
                                 };
-                                
+
                                 this.source.start();
                             }
                         };
                     }
-                    
+
                     // 开始处理缓冲的数据
                     const frames = [...audioBufferQueue];
                     audioBufferQueue = []; // 清空缓冲队列
-                    
+
                     // 解码并播放
                     await streamingContext.decodeOpusFrames(frames);
-                    
+
                 } catch (error) {
                     log(`播放已缓冲的音频出错: ${error.message}`, 'error');
                     isAudioPlaying = false;
                     streamingContext = null;
                 }
             };
-            
+
             // 执行初始化和播放
             initDecoderAndPlay();
         }
@@ -780,7 +934,7 @@
         // 初始化Opus解码器 - 确保完全初始化完成后才返回
         async function initOpusDecoder() {
             if (opusDecoder) return opusDecoder; // 已经初始化
-            
+
             try {
                 // 检查ModuleInstance是否存在
                 if (typeof window.ModuleInstance === 'undefined') {
@@ -792,9 +946,9 @@
                         throw new Error('Opus库未加载，ModuleInstance和Module对象都不存在');
                     }
                 }
-                
+
                 const mod = window.ModuleInstance;
-                
+
                 // 创建解码器对象
                 opusDecoder = {
                     channels: CHANNELS,
@@ -802,55 +956,55 @@
                     frameSize: FRAME_SIZE,
                     module: mod,
                     decoderPtr: null, // 初始为null
-                    
+
                     // 初始化解码器
-                    init: function() {
+                    init: function () {
                         if (this.decoderPtr) return true; // 已经初始化
-                        
+
                         // 获取解码器大小
                         const decoderSize = mod._opus_decoder_get_size(this.channels);
                         log(`Opus解码器大小: ${decoderSize}字节`, 'debug');
-                        
+
                         // 分配内存
                         this.decoderPtr = mod._malloc(decoderSize);
                         if (!this.decoderPtr) {
                             throw new Error("无法分配解码器内存");
                         }
-                        
+
                         // 初始化解码器
                         const err = mod._opus_decoder_init(
                             this.decoderPtr,
                             this.rate,
                             this.channels
                         );
-                        
+
                         if (err < 0) {
                             this.destroy(); // 清理资源
                             throw new Error(`Opus解码器初始化失败: ${err}`);
                         }
-                        
+
                         log("Opus解码器初始化成功", 'success');
                         return true;
                     },
-                    
+
                     // 解码方法
-                    decode: function(opusData) {
+                    decode: function (opusData) {
                         if (!this.decoderPtr) {
                             if (!this.init()) {
                                 throw new Error("解码器未初始化且无法初始化");
                             }
                         }
-                        
+
                         try {
                             const mod = this.module;
-                            
+
                             // 为Opus数据分配内存
                             const opusPtr = mod._malloc(opusData.length);
                             mod.HEAPU8.set(opusData, opusPtr);
-                            
+
                             // 为PCM输出分配内存
                             const pcmPtr = mod._malloc(this.frameSize * 2); // Int16 = 2字节
-                            
+
                             // 解码
                             const decodedSamples = mod._opus_decode(
                                 this.decoderPtr,
@@ -860,46 +1014,46 @@
                                 this.frameSize,
                                 0 // 不使用FEC
                             );
-                            
+
                             if (decodedSamples < 0) {
                                 mod._free(opusPtr);
                                 mod._free(pcmPtr);
                                 throw new Error(`Opus解码失败: ${decodedSamples}`);
                             }
-                            
+
                             // 复制解码后的数据
                             const decodedData = new Int16Array(decodedSamples);
                             for (let i = 0; i < decodedSamples; i++) {
                                 decodedData[i] = mod.HEAP16[(pcmPtr >> 1) + i];
                             }
-                            
+
                             // 释放内存
                             mod._free(opusPtr);
                             mod._free(pcmPtr);
-                            
+
                             return decodedData;
                         } catch (error) {
                             log(`Opus解码错误: ${error.message}`, 'error');
                             return new Int16Array(0);
                         }
                     },
-                    
+
                     // 销毁方法
-                    destroy: function() {
+                    destroy: function () {
                         if (this.decoderPtr) {
                             this.module._free(this.decoderPtr);
                             this.decoderPtr = null;
                         }
                     }
                 };
-                
+
                 // 初始化解码器
                 if (!opusDecoder.init()) {
                     throw new Error("Opus解码器初始化失败");
                 }
-                
+
                 return opusDecoder;
-                
+
             } catch (error) {
                 log(`Opus解码器初始化失败: ${error.message}`, 'error');
                 opusDecoder = null; // 重置为null，以便下次重试
@@ -1132,25 +1286,100 @@
         }
 
         // 连接WebSocket服务器
-        function connectToServer() {
+        async function connectToServer() {
             const url = serverUrlInput.value.trim();
             if (url === '') return;
 
             try {
+                // 获取并验证配置
+                const config = getConfig();
+                if (!validateConfig(config)) {
+                    return;
+                }
+
                 // 检查URL格式
                 if (!url.startsWith('ws://') && !url.startsWith('wss://')) {
                     log('URL格式错误，必须以ws://或wss://开头', 'error');
                     return;
                 }
 
+                // 先检查OTA状态
+                log('正在检查OTA状态...', 'info');
+                const otaUrl = document.getElementById('otaUrl').value.trim();
+
+                try {
+                    const otaResponse = await fetch(otaUrl, {
+                        method: 'POST',
+                        headers: {
+                            'Content-Type': 'application/json',
+                            'Device-Id': config.deviceId,
+                            'Client-Id': config.clientId
+                        },
+                        body: JSON.stringify({
+                            "version": 0,
+                            "uuid": "",
+                            "application": {
+                                "name": "xiaozhi-web-test",
+                                "version": "1.0.0",
+                                "compile_time": "2025-04-16 10:00:00",
+                                "idf_version": "4.4.3",
+                                "elf_sha256": "1234567890abcdef1234567890abcdef1234567890abcdef"
+                            },
+                            "ota": {
+                                "label": "xiaozhi-web-test",
+                            },
+                            "board": {
+                                "type": "xiaozhi-web-test",
+                                "ssid": "xiaozhi-web-test",
+                                "rssi": 0,
+                                "channel": 0,
+                                "ip": "192.168.1.1",
+                                "mac": config.deviceMac
+                            },
+                            "flash_size": 0,
+                            "minimum_free_heap_size": 0,
+                            "mac_address": config.deviceMac,
+                            "chip_model_name": "",
+                            "chip_info": {
+                                "model": 0,
+                                "cores": 0,
+                                "revision": 0,
+                                "features": 0
+                            },
+                            "partition_table": [
+                                {
+                                    "label": "",
+                                    "type": 0,
+                                    "subtype": 0,
+                                    "address": 0,
+                                    "size": 0
+                                }
+                            ]
+                        })
+                    });
+
+                    if (!otaResponse.ok) {
+                        throw new Error(`OTA检查失败: ${otaResponse.status} ${otaResponse.statusText}`);
+                    }
+
+                    const otaResult = await otaResponse.json();
+                    log(`OTA检查结果: ${JSON.stringify(otaResult)}`, 'info');
+
+                    log('OTA检查通过，开始连接WebSocket...', 'success');
+                    document.getElementById('otaStatus').textContent = 'ota已连接';
+                    document.getElementById('otaStatus').style.color = 'green';
+                } catch (error) {
+                    log(`OTA检查错误: ${error.message}`, 'error');
+                    document.getElementById('otaStatus').textContent = 'ota未连接';
+                    document.getElementById('otaStatus').style.color = 'red';
+                }
+
                 // 使用自定义WebSocket实现以添加认证头信息
-                // 注意：浏览器原生WebSocket不支持自定义头，需要通过服务器添加一个代理层
-                // 但我们可以通过URL参数模拟认证信息
                 let connUrl = new URL(url);
 
                 // 添加认证参数
-                connUrl.searchParams.append('device_id', 'web_test_device');
+                connUrl.searchParams.append('device-id', config.deviceId);
-                connUrl.searchParams.append('device_mac', '00:11:22:33:44:55');
+                connUrl.searchParams.append('client-id', config.clientId);
 
                 log(`正在连接: ${connUrl.toString()}`, 'info');
                 websocket = new WebSocket(connUrl.toString());
@@ -1160,7 +1389,7 @@
 
                 websocket.onopen = async () => {
                     log(`已连接到服务器: ${url}`, 'success');
-                    connectionStatus.textContent = '已连接';
+                    connectionStatus.textContent = 'ws已连接';
                     connectionStatus.style.color = 'green';
 
                     // 连接成功后发送hello消息
@@ -1181,7 +1410,7 @@
 
                 websocket.onclose = () => {
                     log('已断开连接', 'info');
-                    connectionStatus.textContent = '已断开';
+                    connectionStatus.textContent = 'ws已断开';
                     connectionStatus.style.color = 'red';
 
                     connectButton.textContent = '连接';
@@ -1196,7 +1425,7 @@
 
                 websocket.onerror = (error) => {
                     log(`WebSocket错误: ${error.message || '未知错误'}`, 'error');
-                    connectionStatus.textContent = '连接错误';
+                    connectionStatus.textContent = 'ws未连接';
                     connectionStatus.style.color = 'red';
                 };
 
@@ -1262,11 +1491,11 @@
                     }
                 };
 
-                connectionStatus.textContent = '正在连接...';
+                connectionStatus.textContent = 'ws未连接';
                 connectionStatus.style.color = 'orange';
             } catch (error) {
                 log(`连接错误: ${error.message}`, 'error');
-                connectionStatus.textContent = '连接失败';
+                connectionStatus.textContent = 'ws未连接';
             }
         }
 
@@ -1275,13 +1504,15 @@
             if (!websocket || websocket.readyState !== WebSocket.OPEN) return;
 
             try {
+                const config = getConfig();
+
                 // 设置设备信息
                 const helloMessage = {
                     type: 'hello',
-                    device_id: 'web_test_device',
+                    device_id: config.deviceId,
-                    device_name: 'Web测试设备',
+                    device_name: config.deviceName,
-                    device_mac: '00:11:22:33:44:55',
+                    device_mac: config.deviceMac,
-                    token: 'your-token1' // 使用config.yaml中配置的token
+                    token: config.token
                 };
 
                 log('发送hello握手消息', 'info');
@@ -1356,6 +1587,34 @@
             connectButton.addEventListener('click', connectToServer);
             document.getElementById('authTestButton').addEventListener('click', testAuthentication);
 
+            // 设备配置面板折叠/展开
+            const toggleButton = document.getElementById('toggleConfig');
+            const configPanel = document.getElementById('configPanel');
+            const deviceMacInput = document.getElementById('deviceMac');
+            const clientIdInput = document.getElementById('clientId');
+            const displayMac = document.getElementById('displayMac');
+            const displayClient = document.getElementById('displayClient');
+
+            // 更新显示的值
+            function updateDisplayValues() {
+                displayMac.textContent = deviceMacInput.value;
+                displayClient.textContent = clientIdInput.value;
+            }
+
+            // 监听输入变化
+            deviceMacInput.addEventListener('input', updateDisplayValues);
+            clientIdInput.addEventListener('input', updateDisplayValues);
+
+            // 初始更新显示值
+            updateDisplayValues();
+
+            // 切换面板显示
+            toggleButton.addEventListener('click', () => {
+                const isExpanded = configPanel.classList.contains('expanded');
+                configPanel.classList.toggle('expanded');
+                toggleButton.textContent = isExpanded ? '编辑' : '收起';
+            });
+
             // 标签页切换
             const tabs = document.querySelectorAll('.tab');
             tabs.forEach(tab => {
@@ -1390,12 +1649,14 @@
         async function testAuthentication() {
             log('开始测试认证...', 'info');
 
+            const config = getConfig();
+
             // 显示服务器配置
             log('-------- 服务器认证配置检查 --------', 'info');
             log('请确认config.yaml中的auth配置：', 'info');
             log('1. server.auth.enabled 为 false 或服务器已正确配置认证', 'info');
             log('2. 如果启用了认证，请确认使用了正确的token', 'info');
-            log('3. 或者在allowed_devices中添加了测试设备MAC：00:11:22:33:44:55', 'info');
+            log(`3. 或者在allowed_devices中添加了测试设备MAC：${config.deviceMac}`, 'info');
 
             const serverUrl = serverUrlInput.value.trim();
             if (!serverUrl) {
@@ -1436,9 +1697,9 @@
                     log('测试2: 尝试带token参数连接...', 'info');
 
                     let url = new URL(serverUrl);
-                    url.searchParams.append('token', 'your-token1');
+                    url.searchParams.append('token', config.token);
-                    url.searchParams.append('device_id', 'web_test_device');
+                    url.searchParams.append('device_id', config.deviceId);
-                    url.searchParams.append('device_mac', '00:11:22:33:44:55');
+                    url.searchParams.append('device_mac', config.deviceMac);
 
                     const ws2 = new WebSocket(url.toString());
 
@@ -1448,9 +1709,9 @@
                         // 尝试发送hello消息
                         const helloMsg = {
                             type: 'hello',
-                            device_id: 'web_test_device',
+                            device_id: config.deviceId,
-                            device_mac: '00:11:22:33:44:55',
+                            device_mac: config.deviceMac,
-                            token: 'your-token1'
+                            token: config.token
                         };
 
                         ws2.send(JSON.stringify(helloMsg));
@@ -2092,19 +2353,19 @@
                 if (opusData.length > 0) {
                     // 将数据添加到缓冲队列
                     audioBufferQueue.push(opusData);
-                    
+
                     // 如果收到的是第一个音频包，开始缓冲过程
                     if (audioBufferQueue.length === 1 && !isAudioBuffering && !isAudioPlaying) {
                         startAudioBuffering();
                     }
                 } else {
                     log('收到空音频数据帧，可能是结束标志', 'warning');
-                    
+
                     // 如果缓冲队列中有数据且没有在播放，立即开始播放
                     if (audioBufferQueue.length > 0 && !isAudioPlaying) {
                         playBufferedAudio();
                     }
-                    
+
                     // 如果正在播放，发送结束信号
                     if (isAudioPlaying && streamingContext) {
                         streamingContext.endOfStream = true;
@@ -2115,6 +2376,31 @@
             }
         }
 
+        // 获取配置值
+        function getConfig() {
+            const deviceMac = document.getElementById('deviceMac').value.trim();
+            return {
+                deviceId: deviceMac,  // 使用MAC地址作为deviceId
+                deviceName: document.getElementById('deviceName').value.trim(),
+                deviceMac: deviceMac,
+                clientId: document.getElementById('clientId').value.trim(),
+                token: document.getElementById('token').value.trim()
+            };
+        }
+
+        // 验证配置
+        function validateConfig(config) {
+            if (!config.deviceMac) {
+                log('设备MAC地址不能为空', 'error');
+                return false;
+            }
+            if (!config.clientId) {
+                log('客户端ID不能为空', 'error');
+                return false;
+            }
+            return true;
+        }
+
         initApp();
     </script>
 </body>