fix:智能体音色未随manager生效bug

* fix:连接manager后无法使用functioncallbug

* fix:意图识别使用llm无法播放音乐bug

* fix：manager第一图识别使用独立llm无法初始化llm的bug

* fix:智能体音色未随manager生效bug

* update:添加edgeTTS音色

main/manager-api/src/main/java/xiaozhi/modules/agent/service/impl/AgentServiceImpl.java

@@ -44,7 +44,7 @@ public class AgentServiceImpl extends BaseServiceImpl<AgentDao, AgentEntity> imp
     @Override
     public PageData<AgentEntity> adminAgentList(Map<String, Object> params) {
         IPage<AgentEntity> page = agentDao.selectPage(
-                getPage(params, "sort", true),
+                getPage(params, "agent_name", true),
                 new QueryWrapper<>());
         return new PageData<>(page.getRecords(), page.getTotal());
     }

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

@@ -231,8 +231,9 @@ public class ConfigServiceImpl implements ConfigService {
             boolean isCache) {
         Map<String, String> selectedModule = new HashMap<>();
 
-        String[] modelTypes = { "VAD", "ASR", "LLM", "TTS", "Memory", "Intent" };
+        String[] modelTypes = { "VAD", "ASR", "TTS", "Memory", "Intent", "LLM" };
-        String[] modelIds = { vadModelId, asrModelId, llmModelId, ttsModelId, memModelId, intentModelId };
+        String[] modelIds = { vadModelId, asrModelId, ttsModelId, memModelId, intentModelId, llmModelId };
+        String intentLLMModelId = null;
 
         for (int i = 0; i < modelIds.length; i++) {
             if (modelIds[i] == null) {
@@ -246,10 +247,27 @@ public class ConfigServiceImpl implements ConfigService {
                 if ("TTS".equals(modelTypes[i]) && voice != null) {
                     ((Map<String, Object>) model.getConfigJson()).put("private_voice", voice);
                 }
+                // 如果是Intent类型，且type=intent_llm，则给他添加附加模型
+                if ("Intent".equals(modelTypes[i])) {
+                    Map<String, Object> map = (Map<String, Object>) model.getConfigJson();
+                    if ("intent_llm".equals(map.get("type"))) {
+                        intentLLMModelId = (String) map.get("llm");
+                        if (intentLLMModelId != null && intentLLMModelId.equals(llmModelId)) {
+                            intentLLMModelId = null;
+                        }
+                    }
+                }
+                // 如果是LLM类型，且intentLLMModelId不为空，则添加附加模型
+                if ("LLM".equals(modelTypes[i]) && intentLLMModelId != null) {
+                    ModelConfigEntity intentLLM = modelConfigService.getModelById(intentLLMModelId, isCache);
+                    typeConfig.put(intentLLM.getId(), intentLLM.getConfigJson());
+                }
             }
             result.put(modelTypes[i], typeConfig);
+
             selectedModule.put(modelTypes[i], model.getId());
         }
+
         result.put("selected_module", selectedModule);
         if (StringUtils.isNotBlank(prompt)) {
             prompt = prompt.replace("{{assistant_name}}", "小智");

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

@@ -221,7 +221,7 @@ public class DeviceServiceImpl extends BaseServiceImpl<DeviceDao, DeviceEntity>
         params.put(Constant.PAGE, dto.getPage());
         params.put(Constant.LIMIT, dto.getLimit());
         IPage<DeviceEntity> page = baseDao.selectPage(
-                getPage(params, "sort", true),
+                getPage(params, "mac_address", true),
                 // 定义查询条件
                 new QueryWrapper<DeviceEntity>()
                         // 必须设备关键词查找

main/manager-api/src/main/java/xiaozhi/modules/sys/service/impl/SysParamsServiceImpl.java

@@ -37,7 +37,7 @@ public class SysParamsServiceImpl extends BaseServiceImpl<SysParamsDao, SysParam
     @Override
     public PageData<SysParamsDTO> page(Map<String, Object> params) {
         IPage<SysParamsEntity> page = baseDao.selectPage(
-                getPage(params, Constant.CREATE_DATE, false),
+                getPage(params, null, false),
                 getWrapper(params));
 
         return getPageData(page, SysParamsDTO.class);

main/manager-api/src/main/java/xiaozhi/modules/timbre/service/impl/TimbreServiceImpl.java

@@ -47,7 +47,7 @@ public class TimbreServiceImpl extends BaseServiceImpl<TimbreDao, TimbreEntity>
         params.put(Constant.PAGE, dto.getPage());
         params.put(Constant.LIMIT, dto.getLimit());
         IPage<TimbreEntity> page = baseDao.selectPage(
-                getPage(params, "sort", true),
+                getPage(params, null, true),
                 // 定义查询条件
                 new QueryWrapper<TimbreEntity>()
                         // 必须按照ttsID查找

main/manager-api/src/main/resources/db/changelog/202504131542.sql

@@ -0,0 +1,3 @@
+-- 对0.3.0版本之前的参数进行修改
+update `sys_params` set param_value = '.mp3;.wav;.p3' where  param_code = 'plugins.play_music.music_ext';
+update `ai_model_config` set config_json =  '{\"type\": \"intent_llm\", \"llm\": \"LLM_ChatGLMLLM\"}' where  id = 'Intent_intent_llm';

main/manager-api/src/main/resources/db/changelog/202504131543.sql

@@ -0,0 +1,18 @@
+-- 对0.3.0版本之前的参数进行修改
+update `sys_params` set param_value = '.mp3;.wav;.p3' where  param_code = 'plugins.play_music.music_ext';
+update `ai_model_config` set config_json =  '{\"type\": \"intent_llm\", \"llm\": \"LLM_ChatGLMLLM\"}' where  id = 'Intent_intent_llm';
+
+-- 添加edge音色
+delete from `ai_tts_voice` where tts_model_id = 'TTS_EdgeTTS';
+INSERT INTO `ai_tts_voice` VALUES 
+('TTS_EdgeTTS0001', 'TTS_EdgeTTS', 'EdgeTTS女声-晓晓', 'zh-CN-XiaoxiaoNeural', '普通话', NULL, NULL, 1, NULL, NULL, NULL, NULL),
+('TTS_EdgeTTS0002', 'TTS_EdgeTTS', 'EdgeTTS男声-云扬', 'zh-CN-YunyangNeural', '普通话', NULL, NULL, 1, NULL, NULL, NULL, NULL),
+('TTS_EdgeTTS0003', 'TTS_EdgeTTS', 'EdgeTTS女声-晓伊', 'zh-CN-XiaoyiNeural', '普通话', NULL, NULL, 1, NULL, NULL, NULL, NULL),
+('TTS_EdgeTTS0004', 'TTS_EdgeTTS', 'EdgeTTS男声-云健', 'zh-CN-YunjianNeural', '普通话', NULL, NULL, 1, NULL, NULL, NULL, NULL),
+('TTS_EdgeTTS0005', 'TTS_EdgeTTS', 'EdgeTTS男声-云希', 'zh-CN-YunxiNeural', '普通话', NULL, NULL, 1, NULL, NULL, NULL, NULL),
+('TTS_EdgeTTS0006', 'TTS_EdgeTTS', 'EdgeTTS男声-云夏', 'zh-CN-YunxiaNeural', '普通话', NULL, NULL, 1, NULL, NULL, NULL, NULL),
+('TTS_EdgeTTS0007', 'TTS_EdgeTTS', 'EdgeTTS女声-辽宁小贝', 'zh-CN-liaoning-XiaobeiNeural', '辽宁', NULL, NULL, 1, NULL, NULL, NULL, NULL),
+('TTS_EdgeTTS0008', 'TTS_EdgeTTS', 'EdgeTTS女声-陕西小妮', 'zh-CN-shaanxi-XiaoniNeural', '陕西', NULL, NULL, 1, NULL, NULL, NULL, NULL),
+('TTS_EdgeTTS0009', 'TTS_EdgeTTS', 'EdgeTTS女声-香港海佳', 'zh-HK-HiuGaaiNeural', '粤语', 'General', 'Friendly, Positive', 1, NULL, NULL, NULL, NULL),
+('TTS_EdgeTTS0010', 'TTS_EdgeTTS', 'EdgeTTS女声-香港海曼', 'zh-HK-HiuMaanNeural', '粤语', 'General', 'Friendly, Positive', 1, NULL, NULL, NULL, NULL),
+('TTS_EdgeTTS0011', 'TTS_EdgeTTS', 'EdgeTTS男声-香港万龙', 'zh-HK-WanLungNeural', '粤语', 'General', 'Friendly, Positive', 1, NULL, NULL, NULL, NULL);

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

@@ -50,4 +50,11 @@ databaseChangeLog:
       changes:
         - sqlFile:
             encoding: utf8
-            path: classpath:db/changelog/202504112058.sql
+            path: classpath:db/changelog/202504112058.sql
+  - changeSet:
+      id: 202504131543
+      author: John
+      changes:
+        - sqlFile:
+            encoding: utf8
+            path: classpath:db/changelog/202504131543.sql

main/manager-web/src/apis/module/model.js

@@ -1,7 +1,6 @@
 import { getServiceUrl } from '../api';
 import RequestService from '../httpRequest';
 
-
 export default {
   // 获取模型配置列表
   getModelList(params, callback) {
@@ -162,21 +161,25 @@ export default {
   // 更新模型配置
   updateModel(params, callback) {
     const { modelType, provideCode, id, formData } = params;
+    const payload = {
+      ...formData,
+      configJson: formData.configJson
+    };
     RequestService.sendRequest()
-      .url(`${getServiceUrl()}/models/${modelType}/${provideCode}/${id}`)
+        .url(`${getServiceUrl()}/models/${modelType}/${provideCode}/${id}`)
-      .method('PUT')
+        .method('PUT')
-      .data(formData)
+        .data(payload)
-      .success((res) => {
+        .success((res) => {
-        RequestService.clearRequestTime();
+            RequestService.clearRequestTime();
-        callback(res);
+            callback(res);
-      })
+        })
-      .fail((err) => {
+        .fail((err) => {
-        console.error('更新模型失败:', err);
+            console.error('更新模型失败:', err);
-        this.$message.error(err.msg || '更新模型失败');
+            this.$message.error(err.msg || '更新模型失败');
-        RequestService.reAjaxFun(() => {
+            RequestService.reAjaxFun(() => {
-          this.updateModel(params, callback);
+                this.updateModel(params, callback);
-        });
+            });
-      }).send();
+        }).send();
   },
   // 设置默认模型
   setDefaultModel(id, callback) {

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

@@ -94,14 +94,6 @@
 <script>
 import Api from '@/apis/api';
 
-const DEFAULT_CONFIG_JSON = {
-    type: "",
-    base_url: "",
-    model_name: "",
-    api_key: "",
-    empty: false
-};
-
 export default {
   name: "ModelEditDialog",
   props: {
@@ -132,7 +124,7 @@ export default {
         docLink: "",
         remark: "",
         sort: 0,
-        configJson: JSON.parse(JSON.stringify(DEFAULT_CONFIG_JSON))
+        configJson: {}
       }
     };
   },
@@ -183,8 +175,11 @@ export default {
             docLink: "",
             remark: "",
             sort: 0,
-            configJson: JSON.parse(JSON.stringify(DEFAULT_CONFIG_JSON))
+            configJson: {}
         };
+        this.dynamicCallInfoFields.forEach(field => {
+          this.$set(this.form.configJson, field.prop, '');
+        });
     },
     resetProviders() {
       this.providers = [];
@@ -266,6 +261,8 @@ export default {
       this.dynamicCallInfoFields.forEach(field => {
         if (!configJson.hasOwnProperty(field.prop)) {
           configJson[field.prop] = '';
+        } else if (typeof configJson[field.prop] !== 'string') {
+          configJson[field.prop] = String(configJson[field.prop]);
         }
       });
 
@@ -280,7 +277,6 @@ export default {
         remark: model.remark,
         sort: Number(model.sort) || 0,
         configJson: {
-          ...DEFAULT_CONFIG_JSON,
           ...configJson
         }
       };

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

@@ -4,10 +4,8 @@
     <el-main style="padding: 20px; display: flex; flex-direction: column;">
       <div class="table-container">
         <h3 class="device-list-title">设备列表</h3>
-        <el-button type="primary" class="add-device-btn" @click="handleAddDevice">
+        <el-table ref="deviceTable" :data="paginatedDeviceList" @selection-change="handleSelectionChange" style="width: 100%; margin-top: 20px" border stripe>
-          + 添加设备
+          <el-table-column type="selection" align="center" width="60"></el-table-column>
-        </el-button>
-        <el-table :data="paginatedDeviceList" style="width: 100%; margin-top: 20px" border stripe>
           <el-table-column label="设备型号" prop="model" flex></el-table-column>
           <el-table-column label="固件版本" prop="firmwareVersion" width="120"></el-table-column>
           <el-table-column label="Mac地址" prop="macAddress"></el-table-column>
@@ -39,9 +37,31 @@
             </template>
           </el-table-column>
         </el-table>
-        <el-pagination class="pagination" @size-change="handleSizeChange" @current-change="handleCurrentChange"
+        <div class="table_bottom">
-          :current-page="currentPage" :page-sizes="[5, 10, 20, 50]" :page-size="pageSize"
+          <div class="ctrl_btn">
-          layout="total, sizes, prev, pager, next, jumper" :total="deviceList.length"></el-pagination>
+            <el-button size="mini" type="primary" class="select-all-btn" @click="toggleAllSelection">
+                {{ isAllSelected ? '取消全选' : '全选' }}
+            </el-button>
+            <el-button type="primary" size="mini" class="add-device-btn" @click="handleAddDevice">
+                新增
+            </el-button>
+          </div>
+          <div class="custom-pagination">
+            <button class="pagination-btn" :disabled="currentPage === 1" @click="goFirst">首页</button>
+            <button class="pagination-btn" :disabled="currentPage === 1" @click="goPrev">上一页</button>
+            <button
+              v-for="page in visiblePages"
+              :key="page"
+              class="pagination-btn"
+              :class="{ active: page === currentPage }"
+              @click="goToPage(page)"
+            >
+              {{ page }}
+            </button>
+            <button class="pagination-btn" :disabled="currentPage === pageCount" @click="goNext">下一页</button>
+            <span class="total-text">共{{ deviceList.length }}条记录</span>
+          </div>
+        </div>
       </div>
       <div class="copyright">
         ©2025 xiaozhi-esp32-server
@@ -62,6 +82,8 @@ export default {
   data() {
     return {
       addDeviceDialogVisible: false,
+       selectedDevices: [],
+      isAllSelected: false,
       currentAgentId: this.$route.query.agentId || '',
       currentPage: 1,
       pageSize: 5,
@@ -75,7 +97,25 @@ export default {
       const start = (this.currentPage - 1) * this.pageSize;
       const end = start + this.pageSize;
       return this.deviceList.slice(start, end);
-    }
+    },
+    pageCount() {
+    return Math.ceil(this.deviceList.length / this.pageSize);
+    },
+    visiblePages() {
+      const pages = [];
+      const maxVisible = 3;
+      let start = Math.max(1, this.currentPage - 1);
+      let end = Math.min(this.pageCount, start + maxVisible - 1);
+
+      if (end - start + 1 < maxVisible) {
+        start = Math.max(1, end - maxVisible + 1);
+      }
+
+      for (let i = start; i <= end; i++) {
+        pages.push(i);
+      }
+      return pages;
+    },
   },
   mounted() {
     const agentId = this.$route.query.agentId;
@@ -84,6 +124,16 @@ export default {
     }
   },
   methods: {
+
+    handleSelectionChange(val) {
+      this.selectedDevices = val;
+      this.isAllSelected = val.length === this.paginatedDeviceList.length;
+    },
+    toggleAllSelection() {
+      this.$refs.deviceTable.toggleAllSelection();
+    },
+
+
     handleAddDevice() {
       this.addDeviceDialogVisible = true;
     },
@@ -115,12 +165,19 @@ export default {
         });
       });
     },
-    handleSizeChange(val) {
+    goFirst() {
-      this.pageSize = val;
+      this.currentPage = 1;
     },
-    handleCurrentChange(val) {
+    goPrev() {
-      this.currentPage = val;
+      if (this.currentPage > 1) this.currentPage--;
     },
+    goNext() {
+      if (this.currentPage < this.pageCount) this.currentPage++;
+    },
+    goToPage(page) {
+      this.currentPage = page;
+    },
+
     fetchBindDevices(agentId) {
       this.loading = true;
       Api.device.getAgentBindDevices(agentId, ({ data }) => {
@@ -180,21 +237,18 @@ export default {
 }
 
 .add-device-btn {
-  float: right;
+  background: linear-gradient(135deg, #6b8cff, #a966ff) !important;
-  background: #409eff;
+  border: none !important;
-  border: none;
+  color: white !important;
-  border-radius: 10px;
+  margin-left: 10px;
-  width: 105px;
   height: 32px;
-  display: flex;
+  padding: 7px 12px;
-  align-items: center;
+  border-radius: 4px !important;
-  justify-content: center;
+  box-shadow: 0 2px 6px rgba(0, 0, 0, 0.1);
-  font-size: 14px;
-  gap: 8px;
-  margin-bottom: 15px;
 
   &:hover {
-    background: #3a8ee6;
+    transform: translateY(-1px);
+    box-shadow: 0 4px 8px rgba(0, 0, 0, 0.15);
   }
 }
 
@@ -213,8 +267,85 @@ export default {
   vertical-align: middle;
 }
 
-.pagination {
+.custom-pagination {
-  margin-top: 20px;
+  display: flex;
-  text-align: right;
+  align-items: center;
+  gap: 8px;
+  margin-top: 15px;
 }
+
+.pagination-btn {
+  min-width: 28px;
+  height: 32px;
+  padding: 0 12px;
+  border-radius: 4px;
+  border: 1px solid #e4e7ed;
+  background: #dee7ff;
+  color: #606266;
+  font-size: 14px;
+  cursor: pointer;
+  transition: all 0.3s ease;
+}
+
+.pagination-btn:first-child,
+.pagination-btn:nth-child(2),
+.pagination-btn:nth-last-child(2) {
+  min-width: 60px;
+}
+
+.pagination-btn:hover {
+  background: #d7dce6;
+}
+
+.pagination-btn:disabled {
+  opacity: 0.6;
+  cursor: not-allowed;
+}
+
+.pagination-btn.active {
+  background: #5f70f3 !important;
+  color: #ffffff !important;
+  border-color: #5f70f3 !important;
+}
+
+.total-text {
+  color: #909399;
+  font-size: 14px;
+  margin-left: 10px;
+}
+
+.table_bottom {
+  display: flex;
+  justify-content: space-between;
+  align-items: center;
+  margin-top: 20px;
+}
+
+.ctrl_btn {
+  display: flex;
+  gap: 8px;
+  padding-left: 26px;
+
+  .el-button {
+    min-width: 72px;
+    height: 32px;
+    padding: 7px 12px;
+    border-radius: 4px;
+    border: none;
+    transition: all 0.3s;
+    box-shadow: 0 2px 6px rgba(0, 0, 0, 0.1);
+
+    &:hover {
+      transform: translateY(-1px);
+      box-shadow: 0 4px 8px rgba(0, 0, 0, 0.15);
+    }
+  }
+
+  .el-button--primary {
+    background: #5f70f3;
+    color: white;
+  }
+}
+
+
 </style>

main/xiaozhi-server/core/connection.py

@@ -104,8 +104,6 @@ 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
-        if self.config["selected_module"]["Intent"] == "function_call":
-            self.use_function_call_mode = True
 
     async def handle_connection(self, ws):
         try:
@@ -222,37 +220,37 @@ class ConnectionHandler:
         )
         if private_config.get("VAD", None) is not None:
             init_vad = True
-            self.config["vad"] = private_config["VAD"]
+            self.config["VAD"] = private_config["VAD"]
             self.config["selected_module"]["VAD"] = private_config["selected_module"][
                 "VAD"
             ]
         if private_config.get("ASR", None) is not None:
             init_asr = True
-            self.config["asr"] = private_config["ASR"]
+            self.config["ASR"] = private_config["ASR"]
             self.config["selected_module"]["ASR"] = private_config["selected_module"][
                 "ASR"
             ]
         if private_config.get("LLM", None) is not None:
             init_llm = True
-            self.config["llm"] = private_config["LLM"]
+            self.config["LLM"] = private_config["LLM"]
             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["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"]
+            self.config["Memory"] = private_config["Memory"]
             self.config["selected_module"]["Memory"] = private_config[
                 "selected_module"
             ]["Memory"]
         if private_config.get("Intent", None) is not None:
             init_intent = True
-            self.config["intent"] = private_config["Intent"]
+            self.config["Intent"] = private_config["Intent"]
             self.config["selected_module"]["Intent"] = private_config[
                 "selected_module"
             ]["Intent"]
@@ -287,17 +285,26 @@ class ConnectionHandler:
         self.memory.init_memory(device_id, self.llm)
 
     def _initialize_intent(self):
+        if (
+            self.config["Intent"][self.config["selected_module"]["Intent"]]["type"]
+            == "function_call"
+        ):
+            self.use_function_call_mode = True
         """初始化意图识别模块"""
         # 获取意图识别配置
         intent_config = self.config["Intent"]
-        intent_type = self.config["selected_module"]["Intent"]
+        intent_type = self.config["Intent"][self.config["selected_module"]["Intent"]][
+            "type"
+        ]
 
         # 如果使用 nointent，直接返回
         if intent_type == "nointent":
             return
         # 使用 intent_llm 模式
         elif intent_type == "intent_llm":
-            intent_llm_name = intent_config["intent_llm"]["llm"]
+            intent_llm_name = intent_config[self.config["selected_module"]["Intent"]][
+                "llm"
+            ]
 
             if intent_llm_name and intent_llm_name in self.config["LLM"]:
                 # 如果配置了专用LLM，则创建独立的LLM实例

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

@@ -57,7 +57,9 @@ class FunctionHandler:
 
     def register_config_functions(self):
         """注册配置中的函数,可以不同客户端使用不同的配置"""
-        for func in self.config["Intent"]["function_call"].get("functions", []):
+        for func in self.config["Intent"][self.config["selected_module"]["Intent"]].get(
+            "functions", []
+        ):
             self.function_registry.register_function(func)
 
         """home assistant需要初始化提示词"""

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

@@ -76,6 +76,11 @@ async def process_intent_result(conn, intent_result, original_text):
             if function_name == "continue_chat":
                 return False
 
+            if function_name == "play_music":
+                funcItem = conn.func_handler.get_function(function_name)
+                if not funcItem:
+                    conn.func_handler.function_registry.register_function("play_music")
+
             function_args = None
             if "arguments" in intent_data["function_call"]:
                 function_args = intent_data["function_call"]["arguments"]

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

@@ -269,14 +269,12 @@ def register_device_type(descriptor):
 
 # 用于接受前端设备推送的搜索iot描述
 async def handleIotDescriptors(conn, descriptors):
-    if not conn.use_function_call_mode:
-        return
     wait_max_time = 5
     while conn.func_handler is None or not conn.func_handler.finish_init:
         await asyncio.sleep(1)
         wait_max_time -= 1
         if wait_max_time <= 0:
-            logger.bind(tag=TAG).error("连接对象没有func_handler")
+            logger.bind(tag=TAG).debug("连接对象没有func_handler")
             return
     """处理物联网描述"""
     functions_changed = False

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

@@ -15,7 +15,15 @@ class LLMProvider(LLMProviderBase):
             self.base_url = config.get("base_url")
         else:
             self.base_url = config.get("url")
-        self.max_tokens = config.get("max_tokens", 500)
+        max_tokens = config.get("max_tokens")
+        if max_tokens is None or max_tokens == "":
+            max_tokens = 500
+
+        try:
+            max_tokens = int(max_tokens)
+        except (ValueError, TypeError):
+            max_tokens = 500
+        self.max_tokens = max_tokens
 
         check_model_key("LLM", self.api_key)
         self.client = openai.OpenAI(api_key=self.api_key, base_url=self.base_url)

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

@@ -12,14 +12,20 @@ class TTSProvider(TTSProviderBase):
         super().__init__(config, delete_audio_file)
         self.model = config.get("model")
         self.access_token = config.get("access_token")
-        self.voice = config.get("voice")
+        if config.get("private_voice"):
+            self.voice = config.get("private_voice")
+        else:
+            self.voice = config.get("voice")
         self.response_format = config.get("response_format")
 
         self.host = "api.coze.cn"
         self.api_url = f"https://{self.host}/v1/audio/speech"
 
     def generate_filename(self, extension=".wav"):
-        return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
+        return os.path.join(
+            self.output_file,
+            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
+        )
 
     async def text_to_speak(self, text, output_file):
         request_json = {
@@ -30,9 +36,11 @@ class TTSProvider(TTSProviderBase):
         }
         headers = {
             "Authorization": f"Bearer {self.access_token}",
-            "Content-Type": "application/json"
+            "Content-Type": "application/json",
         }
-        response = requests.request("POST", self.api_url, json=request_json, headers=headers)
+        response = requests.request(
+            "POST", self.api_url, json=request_json, headers=headers
+        )
         data = response.content
         file_to_save = open(output_file, "wb")
         file_to_save.write(data)

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

@@ -18,7 +18,12 @@ class TTSProvider(TTSProviderBase):
         self.appid = config.get("appid")
         self.access_token = config.get("access_token")
         self.cluster = config.get("cluster")
-        self.voice = config.get("voice")
+
+        if config.get("private_voice"):
+            self.voice = config.get("private_voice")
+        else:
+            self.voice = config.get("voice")
+
         self.api_url = config.get("api_url")
         self.authorization = config.get("authorization")
         self.header = {"Authorization": f"{self.authorization}{self.access_token}"}

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

@@ -8,20 +8,26 @@ from core.providers.tts.base import TTSProviderBase
 class TTSProvider(TTSProviderBase):
     def __init__(self, config, delete_audio_file):
         super().__init__(config, delete_audio_file)
-        self.voice = config.get("voice")
+        if config.get("private_voice"):
+            self.voice = config.get("private_voice")
+        else:
+            self.voice = config.get("voice")
 
     def generate_filename(self, extension=".mp3"):
-        return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
+        return os.path.join(
+            self.output_file,
+            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
+        )
 
     async def text_to_speak(self, text, output_file):
         communicate = edge_tts.Communicate(text, voice=self.voice)
         # 确保目录存在并创建空文件
         os.makedirs(os.path.dirname(output_file), exist_ok=True)
-        with open(output_file, 'wb') as f:
+        with open(output_file, "wb") as f:
             pass
-        
+
         # 流式写入音频数据
-        with open(output_file, 'ab') as f:  # 改为追加模式避免覆盖
+        with open(output_file, "ab") as f:  # 改为追加模式避免覆盖
             async for chunk in communicate.stream():
                 if chunk["type"] == "audio":  # 只处理音频数据块
                     f.write(chunk["data"])

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

@@ -12,28 +12,33 @@ class TTSProvider(TTSProviderBase):
         self.group_id = config.get("group_id")
         self.api_key = config.get("api_key")
         self.model = config.get("model")
-        self.voice_id = config.get("voice_id")
+        if config.get("private_voice"):
+            self.voice_id = config.get("private_voice")
+        else:
+            self.voice_id = config.get("voice_id")
 
         default_voice_setting = {
             "voice_id": "female-shaonv",
             "speed": 1,
             "vol": 1,
             "pitch": 0,
-            "emotion": "happy"
+            "emotion": "happy",
-        }
-        default_pronunciation_dict = {
-            "tone": [
-                "处理/(chu3)(li3)", "危险/dangerous"
-            ]
         }
+        default_pronunciation_dict = {"tone": ["处理/(chu3)(li3)", "危险/dangerous"]}
         defult_audio_setting = {
             "sample_rate": 32000,
             "bitrate": 128000,
             "format": "mp3",
-            "channel": 1
+            "channel": 1,
+        }
+        self.voice_setting = {
+            **default_voice_setting,
+            **config.get("voice_setting", {}),
+        }
+        self.pronunciation_dict = {
+            **default_pronunciation_dict,
+            **config.get("pronunciation_dict", {}),
         }
-        self.voice_setting = {**default_voice_setting, **config.get("voice_setting", {})}
-        self.pronunciation_dict = {**default_pronunciation_dict, **config.get("pronunciation_dict", {})}
         self.audio_setting = {**defult_audio_setting, **config.get("audio_setting", {})}
         self.timber_weights = config.get("timber_weights", [])
 
@@ -44,11 +49,14 @@ class TTSProvider(TTSProviderBase):
         self.api_url = f"https://{self.host}/v1/t2a_v2?GroupId={self.group_id}"
         self.header = {
             "Content-Type": "application/json",
-            "Authorization": f"Bearer {self.api_key}"
+            "Authorization": f"Bearer {self.api_key}",
         }
 
     def generate_filename(self, extension=".mp3"):
-        return os.path.join(self.output_file, f"tts-{__name__}{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
+        return os.path.join(
+            self.output_file,
+            f"tts-{__name__}{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
+        )
 
     async def text_to_speak(self, text, output_file):
         request_json = {
@@ -65,13 +73,17 @@ class TTSProvider(TTSProviderBase):
             request_json["voice_setting"]["voice_id"] = ""
 
         try:
-            resp = requests.post(self.api_url, json.dumps(request_json), headers=self.header)
+            resp = requests.post(
+                self.api_url, json.dumps(request_json), headers=self.header
+            )
             # 检查返回请求数据的status_code是否为0
             if resp.json()["base_resp"]["status_code"] == 0:
-                data = resp.json()['data']['audio']
+                data = resp.json()["data"]["audio"]
                 file_to_save = open(output_file, "wb")
                 file_to_save.write(bytes.fromhex(data))
             else:
-                raise Exception(f"{__name__} status_code: {resp.status_code} response: {resp.content}")
+                raise Exception(
+                    f"{__name__} status_code: {resp.status_code} response: {resp.content}"
+                )
         except Exception as e:
-            raise Exception(f"{__name__} error: {e}")
+            raise Exception(f"{__name__} error: {e}")

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

@@ -16,7 +16,10 @@ class TTSProvider(TTSProviderBase):
         self.api_key = config.get("api_key")
         self.api_url = config.get("api_url", "https://api.openai.com/v1/audio/speech")
         self.model = config.get("model", "tts-1")
-        self.voice = config.get("voice", "alloy")
+        if config.get("private_voice"):
+            self.voice = config.get("private_voice")
+        else:
+            self.voice = config.get("voice", "alloy")
         self.response_format = "wav"
         self.speed = config.get("speed", 1.0)
         self.output_file = config.get("output_dir", "tmp/")

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

@@ -10,7 +10,10 @@ class TTSProvider(TTSProviderBase):
         super().__init__(config, delete_audio_file)
         self.model = config.get("model")
         self.access_token = config.get("access_token")
-        self.voice = config.get("voice")
+        if config.get("private_voice"):
+            self.voice = config.get("private_voice")
+        else:
+            self.voice = config.get("voice")
         self.response_format = config.get("response_format")
         self.sample_rate = config.get("sample_rate")
         self.speed = config.get("speed")
@@ -20,7 +23,10 @@ class TTSProvider(TTSProviderBase):
         self.api_url = f"https://{self.host}/v1/audio/speech"
 
     def generate_filename(self, extension=".wav"):
-        return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
+        return os.path.join(
+            self.output_file,
+            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
+        )
 
     async def text_to_speak(self, text, output_file):
         request_json = {
@@ -31,9 +37,11 @@ class TTSProvider(TTSProviderBase):
         }
         headers = {
             "Authorization": f"Bearer {self.access_token}",
-            "Content-Type": "application/json"
+            "Content-Type": "application/json",
         }
-        response = requests.request("POST", self.api_url, json=request_json, headers=headers)
+        response = requests.request(
+            "POST", self.api_url, json=request_json, headers=headers
+        )
         data = response.content
         file_to_save = open(output_file, "wb")
         file_to_save.write(data)

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

@@ -16,7 +16,10 @@ class TTSProvider(TTSProviderBase):
         self.appid = config.get("appid")
         self.secret_id = config.get("secret_id")
         self.secret_key = config.get("secret_key")
-        self.voice = config.get("voice")
+        if config.get("private_voice"):
+            self.voice = config.get("private_voice")
+        else:
+            self.voice = config.get("voice")
         self.api_url = "https://tts.tencentcloudapi.com"  # 正确的API端点
         self.region = config.get("region")
         self.output_file = config.get("output_dir")
@@ -25,35 +28,36 @@ class TTSProvider(TTSProviderBase):
         """生成鉴权请求头"""
         # 获取当前UTC时间戳
         timestamp = int(time.time())
-        
+
         # 使用UTC时间计算日期
-        utc_date = datetime.fromtimestamp(timestamp, tz=timezone.utc).strftime('%Y-%m-%d')
+        utc_date = datetime.fromtimestamp(timestamp, tz=timezone.utc).strftime(
-        
+            "%Y-%m-%d"
+        )
+
         # 服务名称必须是 "tts"
         service = "tts"
-        
+
         # 拼接凭证范围
         credential_scope = f"{utc_date}/{service}/tc3_request"
-        
+
         # 使用TC3-HMAC-SHA256签名方法
         algorithm = "TC3-HMAC-SHA256"
-        
+
         # 构建规范请求字符串
         http_request_method = "POST"
         canonical_uri = "/"
         canonical_querystring = ""
-        
+
         # 请求头必须包含host和content-type，且按字典序排列
         canonical_headers = (
-            f"content-type:application/json\n"
+            f"content-type:application/json\n" f"host:tts.tencentcloudapi.com\n"
-            f"host:tts.tencentcloudapi.com\n"
         )
         signed_headers = "content-type;host"
-        
+
         # 请求体哈希值
         payload = json.dumps(request_body)
-        payload_hash = hashlib.sha256(payload.encode('utf-8')).hexdigest()
+        payload_hash = hashlib.sha256(payload.encode("utf-8")).hexdigest()
-        
+
         # 构建规范请求字符串
         canonical_request = (
             f"{http_request_method}\n"
@@ -63,10 +67,12 @@ class TTSProvider(TTSProviderBase):
             f"{signed_headers}\n"
             f"{payload_hash}"
         )
-        
+
         # 计算规范请求的哈希值
-        hashed_canonical_request = hashlib.sha256(canonical_request.encode('utf-8')).hexdigest()
+        hashed_canonical_request = hashlib.sha256(
-        
+            canonical_request.encode("utf-8")
+        ).hexdigest()
+
         # 构建待签名字符串
         string_to_sign = (
             f"{algorithm}\n"
@@ -74,19 +80,19 @@ class TTSProvider(TTSProviderBase):
             f"{credential_scope}\n"
             f"{hashed_canonical_request}"
         )
-        
+
         # 计算签名密钥
-        secret_date = self._hmac_sha256(f"TC3{self.secret_key}".encode('utf-8'), utc_date)
+        secret_date = self._hmac_sha256(
+            f"TC3{self.secret_key}".encode("utf-8"), utc_date
+        )
         secret_service = self._hmac_sha256(secret_date, service)
         secret_signing = self._hmac_sha256(secret_service, "tc3_request")
-        
+
         # 计算签名
         signature = hmac.new(
-            secret_signing, 
+            secret_signing, string_to_sign.encode("utf-8"), hashlib.sha256
-            string_to_sign.encode('utf-8'), 
-            hashlib.sha256
         ).hexdigest()
-        
+
         # 构建授权头
         authorization = (
             f"{algorithm} "
@@ -94,7 +100,7 @@ class TTSProvider(TTSProviderBase):
             f"SignedHeaders={signed_headers}, "
             f"Signature={signature}"
         )
-        
+
         # 构建请求头
         headers = {
             "Content-Type": "application/json",
@@ -104,19 +110,22 @@ class TTSProvider(TTSProviderBase):
             "X-TC-Timestamp": str(timestamp),
             "X-TC-Version": "2019-08-23",
             "X-TC-Region": self.region,
-            "X-TC-Language": "zh-CN"
+            "X-TC-Language": "zh-CN",
         }
-        
+
         return headers
-    
+
     def _hmac_sha256(self, key, msg):
         """HMAC-SHA256加密"""
         if isinstance(msg, str):
-            msg = msg.encode('utf-8')
+            msg = msg.encode("utf-8")
         return hmac.new(key, msg, hashlib.sha256).digest()
 
     def generate_filename(self, extension=".wav"):
-        return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
+        return os.path.join(
+            self.output_file,
+            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
+        )
 
     async def text_to_speak(self, text, output_file):
         # 构建请求体
@@ -129,19 +138,23 @@ class TTSProvider(TTSProviderBase):
         try:
             # 获取请求头（每次请求都重新生成，以确保时间戳和签名是最新的）
             headers = self._get_auth_headers(request_json)
-            
+
             # 发送请求
-            resp = requests.post(self.api_url, json.dumps(request_json), headers=headers)
+            resp = requests.post(
-            
+                self.api_url, json.dumps(request_json), headers=headers
+            )
+
             # 检查响应
             if resp.status_code == 200:
                 response_data = resp.json()
-                
+
                 # 检查是否成功
                 if response_data.get("Response", {}).get("Error") is not None:
                     error_info = response_data["Response"]["Error"]
-                    raise Exception(f"API返回错误: {error_info['Code']}: {error_info['Message']}")
+                    raise Exception(
-                
+                        f"API返回错误: {error_info['Code']}: {error_info['Message']}"
+                    )
+
                 # 提取音频数据
                 audio_data = response_data["Response"].get("Audio")
                 if audio_data:
@@ -151,6 +164,8 @@ class TTSProvider(TTSProviderBase):
                 else:
                     raise Exception(f"{__name__}: 没有返回音频数据: {response_data}")
             else:
-                raise Exception(f"{__name__} status_code: {resp.status_code} response: {resp.content}")
+                raise Exception(
+                    f"{__name__} status_code: {resp.status_code} response: {resp.content}"
+                )
         except Exception as e:
-            raise Exception(f"{__name__} error: {e}")
+            raise Exception(f"{__name__} error: {e}")

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

@@ -10,8 +10,14 @@ from core.providers.tts.base import TTSProviderBase
 class TTSProvider(TTSProviderBase):
     def __init__(self, config, delete_audio_file):
         super().__init__(config, delete_audio_file)
-        self.url = config.get("url", "https://u95167-bd74-2aef8085.westx.seetacloud.com:8443/flashsummary/tts?token=")
+        self.url = config.get(
-        self.voice_id = config.get("voice_id", 1695)
+            "url",
+            "https://u95167-bd74-2aef8085.westx.seetacloud.com:8443/flashsummary/tts?token=",
+        )
+        if config.get("private_voice"):
+            self.voice_id = int(config.get("private_voice"))
+        else:
+            self.voice_id = int(config.get("voice_id", 1695))
         self.token = config.get("token")
         self.to_lang = config.get("to_lang")
         self.volume_change_dB = config.get("volume_change_dB", 0)
@@ -21,37 +27,45 @@ class TTSProvider(TTSProviderBase):
         self.pitch_factor = config.get("pitch_factor", 0)
         self.format = config.get("format", "mp3")
         self.emotion = config.get("emotion", 1)
-        self.header = {
+        self.header = {"Content-Type": "application/json"}
-            "Content-Type": "application/json"
-        }
 
     def generate_filename(self, extension=".mp3"):
-        return os.path.join(self.output_file, f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}")
+        return os.path.join(
+            self.output_file,
+            f"tts-{datetime.now().date()}@{uuid.uuid4().hex}{extension}",
+        )
 
     async def text_to_speak(self, text, output_file):
-        url = f'{self.url}{self.token}'
+        url = f"{self.url}{self.token}"
         result = "firefly"
-        payload = json.dumps({
+        payload = json.dumps(
-            "to_lang": self.to_lang,
+            {
-            "text": text,
+                "to_lang": self.to_lang,
-            "emotion": self.emotion,
+                "text": text,
-            "format": self.format,
+                "emotion": self.emotion,
-            "volume_change_dB": self.volume_change_dB,
+                "format": self.format,
-            "voice_id": self.voice_id,
+                "volume_change_dB": self.volume_change_dB,
-            "pitch_factor": self.pitch_factor,
+                "voice_id": self.voice_id,
-            "speed_factor": self.speed_factor,
+                "pitch_factor": self.pitch_factor,
-            "token": self.token
+                "speed_factor": self.speed_factor,
-        })
+                "token": self.token,
+            }
+        )
 
         resp = requests.request("POST", url, data=payload)
         if resp.status_code != 200:
             return None
         resp_json = resp.json()
         try:
-            result = resp_json['url'] + ':' + str(
+            result = (
-                resp_json[
+                resp_json["url"]
-                    'port']) + '/flashsummary/retrieveFileData?stream=True&token=' + self.token + '&voice_audio_path=' + \
+                + ":"
-                     resp_json['voice_path']
+                + str(resp_json["port"])
+                + "/flashsummary/retrieveFileData?stream=True&token="
+                + self.token
+                + "&voice_audio_path="
+                + resp_json["voice_path"]
+            )
         except Exception as e:
             print("error:", e)
 

main/xiaozhi-server/core/providers/vad/silero.py

@@ -42,7 +42,8 @@ class VADProvider(VADProviderBase):
                 audio_tensor = torch.from_numpy(audio_float32)
 
                 # 检测语音活动
-                speech_prob = self.model(audio_tensor, 16000).item()
+                with torch.no_grad():
+                    speech_prob = self.model(audio_tensor, 16000).item()
                 client_have_voice = speech_prob >= self.vad_threshold
 
                 # 如果之前有声音，但本次没有声音，且与上次有声音的时间查已经超过了静默阈值，则认为已经说完一句话

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

@@ -1,34 +1,43 @@
-from plugins_func.register import register_function,ToolType, ActionResponse, Action
+from plugins_func.register import register_function, ToolType, ActionResponse, Action
 from config.logger import setup_logging
 
 TAG = __name__
 logger = setup_logging()
 
 handle_exit_intent_function_desc = {
-                "type": "function",
+    "type": "function",
-                "function": {
+    "function": {
-                    "name": "handle_exit_intent",
+        "name": "handle_exit_intent",
-                    "description": "当用户想结束对话或需要退出系统时调用",
+        "description": "当用户想结束对话或需要退出系统时调用",
-                    "parameters": {
+        "parameters": {
-                        "type": "object",
+            "type": "object",
-                        "properties": {
+            "properties": {
-                            "say_goodbye": {
+                "say_goodbye": {
-                                "type": "string",
+                    "type": "string",
-                                "description": "和用户友好结束对话的告别语"
+                    "description": "和用户友好结束对话的告别语",
-                            }
-                        },
-                        "required": ["say_goodbye"]
-                    }
                 }
-            }
+            },
+            "required": ["say_goodbye"],
+        },
+    },
+}
 
-@register_function('handle_exit_intent', handle_exit_intent_function_desc, ToolType.SYSTEM_CTL)
+
-def handle_exit_intent(conn, say_goodbye: str):
+@register_function(
+    "handle_exit_intent", handle_exit_intent_function_desc, ToolType.SYSTEM_CTL
+)
+def handle_exit_intent(conn, say_goodbye: str | None = None):
     # 处理退出意图
     try:
+        if say_goodbye is None:
+            say_goodbye = "再见，祝您生活愉快！"
         conn.close_after_chat = True
         logger.bind(tag=TAG).info(f"退出意图已处理:{say_goodbye}")
-        return ActionResponse(action=Action.RESPONSE, result="退出意图已处理", response=say_goodbye)
+        return ActionResponse(
+            action=Action.RESPONSE, result="退出意图已处理", response=say_goodbye
+        )
     except Exception as e:
         logger.bind(tag=TAG).error(f"处理退出意图错误: {e}")
-        return ActionResponse(action=Action.NONE, result="退出意图处理失败", response="")
+        return ActionResponse(
+            action=Action.NONE, result="退出意图处理失败", response=""
+        )

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

@@ -9,7 +9,9 @@ HASS_CACHE = {}
 
 def append_devices_to_prompt(conn):
     if conn.use_function_call_mode:
-        funcs = conn.config["Intent"]["function_call"].get("functions", [])
+        funcs = conn.config["Intent"][conn.config["selected_module"]["Intent"]].get(
+            "functions", []
+        )
         if "hass_get_state" in funcs or "hass_set_state" in funcs:
             prompt = "下面是我家智能设备，可以通过homeassistant控制\n"
             devices = conn.config["plugins"]["home_assistant"].get("devices", [])
@@ -26,7 +28,9 @@ def initialize_hass_handler(conn):
     global HASS_CACHE
     if HASS_CACHE == {}:
         if conn.use_function_call_mode:
-            funcs = conn.config["Intent"]["function_call"].get("functions", [])
+            funcs = conn.config["Intent"][conn.config["selected_module"]["Intent"]].get(
+                "functions", []
+            )
             if "hass_get_state" in funcs or "hass_set_state" in funcs:
                 HASS_CACHE["base_url"] = conn.config["plugins"]["home_assistant"].get(
                     "base_url"