Merge branch 'main' into web-vue-modify-device

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

@@ -171,7 +171,13 @@ public class ConfigServiceImpl implements ConfigService {
             switch (param.getValueType().toLowerCase()) {
                 case "number":
                     try {
-                        current.put(lastKey, Double.parseDouble(value));
+                        double doubleValue = Double.parseDouble(value);
+                        // 如果数值是整数形式，则转换为Integer
+                        if (doubleValue == (int) doubleValue) {
+                            current.put(lastKey, (int) doubleValue);
+                        } else {
+                            current.put(lastKey, doubleValue);
+                        }
                     } catch (NumberFormatException e) {
                         current.put(lastKey, value);
                     }

main/manager-api/src/main/java/xiaozhi/modules/security/config/ShiroConfig.java

@@ -76,6 +76,7 @@ public class ShiroConfig {
         filterMap.put("/favicon.ico", "anon");
         filterMap.put("/user/captcha", "anon");
         filterMap.put("/user/login", "anon");
+        filterMap.put("/user/pub-config", "anon");
         filterMap.put("/user/register", "anon");
         filterMap.put("/config/server-base", "anon");
         filterMap.put("/config/agent-models", "anon");

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

@@ -1,6 +1,8 @@
 package xiaozhi.modules.security.controller;
 
 import java.io.IOException;
+import java.util.HashMap;
+import java.util.Map;
 
 import org.springframework.web.bind.annotation.GetMapping;
 import org.springframework.web.bind.annotation.PostMapping;
@@ -111,4 +113,12 @@ public class LoginController {
         sysUserTokenService.changePassword(userId, passwordDTO);
         return new Result<>();
     }
+
+    @GetMapping("/pub-config")
+    @Operation(summary = "公共配置")
+    public Result<Map<String, Object>> pubConfig() {
+        Map<String, Object> config = new HashMap<>();
+        config.put("version", "0.3.3");
+        return new Result<Map<String, Object>>().ok(config);
+    }
 }

main/manager-web/.env.development

@@ -1,4 +1 @@
-# 暂时使用群主的接口
-# VUE_APP_API_BASE_URL=https://2662r3426b.vicp.fun/xiaozhi
-# 如果本地开发，请使用以下接口
-VUE_APP_API_BASE_URL=http://localhost:8002/xiaozhi
+VUE_APP_API_BASE_URL=/xiaozhi

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

@@ -106,7 +106,7 @@ export default {
     },
     // 修改用户状态
     changeUserStatus(status, userIds, successCallback) {
-        console.log(555,userIds)
+        console.log(555, userIds)
         RequestService.sendRequest()
             .url(`${getServiceUrl()}/admin/users/changeStatus/${status}`)
             .method('put')
@@ -122,4 +122,20 @@ export default {
                 })
             }).send()
     },
+    // 获取公共配置
+    getPubConfig(callback) {
+        RequestService.sendRequest()
+            .url(`${getServiceUrl()}/user/pub-config`)
+            .method('GET')
+            .success((res) => {
+                RequestService.clearRequestTime();
+                callback(res);
+            })
+            .fail((err) => {
+                console.error('获取公共配置失败:', err);
+                RequestService.reAjaxFun(() => {
+                    this.getPubConfig(callback);
+                });
+            }).send();
+    },
 }

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

@@ -0,0 +1,39 @@
+<template>
+    <div class="copyright">
+        ©2025 xiaozhi-esp32-server v{{ version }}
+    </div>
+</template>
+
+<script>
+import Api from '@/apis/api';
+
+export default {
+    name: 'VersionFooter',
+    data() {
+        return {
+            version: ''
+        }
+    },
+    mounted() {
+        this.getSystemVersion();
+    },
+    methods: {
+        getSystemVersion() {
+            const storedVersion = sessionStorage.getItem('systemVersion');
+            if (storedVersion) {
+                this.version = storedVersion;
+                return;
+            }
+
+            Api.user.getPubConfig(({ data }) => {
+                if (data.code === 0 && data.data.version) {
+                    this.version = data.data.version;
+                    sessionStorage.setItem('systemVersion', data.data.version);
+                }
+            });
+        }
+    }
+}
+</script>
+
+<style scoped></style>

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

@@ -88,6 +88,7 @@
 
     <AddDeviceDialog :visible.sync="addDeviceDialogVisible" :agent-id="currentAgentId"
       @refresh="fetchBindDevices(currentAgentId)" />
+
   </div>
 </template>
 
@@ -131,6 +132,7 @@ export default {
     },
     pageCount() {
       return Math.ceil(this.filteredDeviceList.length / this.pageSize);
+
     },
     visiblePages() {
       const pages = [];
@@ -523,4 +525,5 @@ export default {
   color: #5a64b5;
 }
 
+
 </style>

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

@@ -3,21 +3,15 @@
     <HeaderBar />
 
     <div class="operation-bar">
-        <h2 class="page-title">{{ modelTypeText }}</h2>
+      <h2 class="page-title">{{ modelTypeText }}</h2>
       <div class="action-group">
-            <div class="search-group">
-                <el-input
-                    placeholder="请输入模型名称查询"
-                    v-model="search"
-                    class="search-input"
-                    clearable
-                    @keyup.enter.native="handleSearch"
-                    style="width: 240px"
-                />
-                <el-button class="btn-search" @click="handleSearch">
-                  搜索
-                </el-button>
-            </div>
+        <div class="search-group">
+          <el-input placeholder="请输入模型名称查询" v-model="search" class="search-input" clearable
+            @keyup.enter.native="handleSearch" style="width: 240px" />
+          <el-button class="btn-search" @click="handleSearch">
+            搜索
+          </el-button>
+        </div>
       </div>
     </div>
 
@@ -93,9 +87,9 @@
 
           <div class="table-footer">
             <div class="batch-actions">
-              <el-button size="mini" type="primary" @click="selectAll" >
+              <el-button size="mini" type="primary" @click="selectAll">
                 {{ isAllSelected ?
-                '取消全选' : '全选' }}
+                  '取消全选' : '全选' }}
               </el-button>
               <el-button type="success" size="mini" @click="addModel" class="add-btn">
                 新增
@@ -125,10 +119,6 @@
       <TtsModel :visible.sync="ttsDialogVisible" :ttsModelId="selectedTtsModelId" />
       <AddModelDialog :modelType="activeTab" :visible.sync="addDialogVisible" @confirm="handleAddConfirm" />
     </div>
-
-<!--    <div class="copyright">-->
-<!--      ©2025 xiaozhi-esp32-server-->
-<!--    </div>-->
   </div>
 </template>
 
@@ -639,7 +629,6 @@ export default {
   gap: 8px;
 }
 
-
 .title-wrapper {
   display: flex;
   align-items: center;

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

@@ -42,7 +42,7 @@
             <div class="table_bottom">
               <div class="ctrl_btn">
                 <el-button size="mini" type="primary" class="select-all-btn" @click="handleSelectAll">
-                    {{ isAllSelected ? '取消全选' : '全选' }}
+                  {{ isAllSelected ? '取消全选' : '全选' }}
                 </el-button>
                 <el-button size="mini" type="success" icon="el-icon-circle-check" @click="batchEnable">启用</el-button>
                 <el-button size="mini" type="warning" @click="batchDisable"><i
@@ -70,7 +70,6 @@
       </div>
     </div>
 
-<!-- <div class="copyright">©2025 xiaozhi-esp32-server</div> -->
     <view-password-dialog :visible.sync="showViewPassword" :password="currentPassword" />
   </div>
 </template>

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

@@ -35,11 +35,11 @@
             @deviceManage="handleDeviceManage" @delete="handleDeleteAgent" />
         </div>
       </div>
-      <div class="copyright">
-        ©2025 xiaozhi-esp32-server
-      </div>
       <AddWisdomBodyDialog :visible.sync="addDeviceDialogVisible" @confirm="handleWisdomBodyAdded" />
     </el-main>
+    <el-footer>
+      <version-footer />
+    </el-footer>
   </div>
 
 </template>
@@ -49,10 +49,11 @@ import Api from '@/apis/api';
 import AddWisdomBodyDialog from '@/components/AddWisdomBodyDialog.vue';
 import DeviceItem from '@/components/DeviceItem.vue';
 import HeaderBar from '@/components/HeaderBar.vue';
+import VersionFooter from '@/components/VersionFooter.vue';
 
 export default {
   name: 'HomePage',
-  components: { DeviceItem, AddWisdomBodyDialog, HeaderBar },
+  components: { DeviceItem, AddWisdomBodyDialog, HeaderBar, VersionFooter },
   data() {
     return {
       addDeviceDialogVisible: false,

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

@@ -51,9 +51,7 @@
         </div>
       </el-main>
       <el-footer>
-        <div class="copyright">
-          ©2025 xiaozhi-esp32-server
-        </div>
+        <version-footer />
       </el-footer>
     </el-container>
   </div>
@@ -61,11 +59,14 @@
 
 <script>
 import Api from '@/apis/api';
+import VersionFooter from '@/components/VersionFooter.vue';
 import { getUUID, goToPage, showDanger, showSuccess } from '@/utils';
 
-
 export default {
   name: 'login',
+  components: {
+    VersionFooter
+  },
   data() {
     return {
       activeName: "username",
@@ -76,11 +77,13 @@ export default {
         captchaId: ''
       },
       captchaUuid: '',
-      captchaUrl: ''
+      captchaUrl: '',
+      version: ''
     }
   },
   mounted() {
     this.fetchCaptcha();
+    this.getSystemVersion();
   },
   methods: {
     fetchCaptcha() {
@@ -144,6 +147,21 @@ export default {
 
     goToRegister() {
       goToPage('/register')
+    },
+
+    getSystemVersion() {
+      const storedVersion = sessionStorage.getItem('systemVersion');
+      if (storedVersion) {
+        this.version = storedVersion;
+        return;
+      }
+
+      Api.user.getPubConfig(({ data }) => {
+        if (data.code === 0 && data.data.version) {
+          this.version = data.data.version;
+          sessionStorage.setItem('systemVersion', data.data.version);
+        }
+      });
     }
   }
 }

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

@@ -72,9 +72,7 @@
 
       <!-- 保持相同的页脚 -->
       <el-footer>
-        <div class="copyright">
-          ©2025 xiaozhi-esp32-server
-        </div>
+        <version-footer />
       </el-footer>
     </el-container>
   </div>
@@ -82,10 +80,14 @@
 
 <script>
 import Api from '@/apis/api';
+import VersionFooter from '@/components/VersionFooter.vue';
 import { getUUID, goToPage, showDanger, showSuccess } from '@/utils';
 
 export default {
   name: 'register',
+  components: {
+    VersionFooter
+  },
   data() {
     return {
       form: {

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

@@ -81,9 +81,7 @@
           </div>
         </div>
       </div>
-<!--      <div class="copyright">-->
-<!--        ©2025 xiaozhi-esp32-server-->
-<!--      </div>-->
+
     </el-main>
   </div>
 </template>

main/manager-web/vue.config.js

@@ -15,6 +15,10 @@ module.exports = defineConfig({
   devServer: {
     port: 8001, // 指定端口为 8001
     proxy: {
+      '/xiaozhi': {
+        target: 'http://127.0.0.1:8002',
+        changeOrigin: true
+      }
     },
     client: {
       overlay: false, // 不显示 webpack 错误覆盖层

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 = "0.3.1"
+SERVER_VERSION = "0.3.3"
 
 
 def get_module_abbreviation(module_name, module_dict):
@@ -25,6 +25,12 @@ def build_module_string(selected_module):
     )
 
 
+def formatter(record):
+    """为没有 tag 的日志添加默认值"""
+    record["extra"].setdefault("tag", record["name"])
+    return record["message"]
+
+
 def setup_logging():
     """从配置文件中读取日志配置，并设置日志输出格式和级别"""
     config = load_config()
@@ -56,9 +62,14 @@ def setup_logging():
     logger.remove()
 
     # 输出到控制台
-    logger.add(sys.stdout, format=log_format, level=log_level)
+    logger.add(sys.stdout, format=log_format, level=log_level, filter=formatter)
 
     # 输出到文件
-    logger.add(os.path.join(log_dir, log_file), format=log_format_file, level=log_level)
+    logger.add(
+        os.path.join(log_dir, log_file),
+        format=log_format_file,
+        level=log_level,
+        filter=formatter,
+    )
 
     return logger

main/xiaozhi-server/core/connection.py

@@ -204,7 +204,7 @@ class ConnectionHandler:
                 self.headers.get("device-id", None),
                 self.headers.get("client-id", None),
             )
-            private_config["delete_audio"] = self.config["delete_audio"]
+            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}")
         except Exception as e:
             self.logger.bind(tag=TAG).error(f"获取差异化配置失败: {e}")
@@ -335,10 +335,8 @@ class ConnectionHandler:
 
     def change_system_prompt(self, prompt):
         self.prompt = prompt
-        # 找到原来的role==system，替换原来的系统提示
-        for m in self.dialogue.dialogue:
-            if m.role == "system":
-                m.content = prompt
+        # 更新系统prompt至上下文
+        self.dialogue.update_system_message(self.prompt)
 
     def chat(self, query):
 
@@ -702,7 +700,7 @@ class ConnectionHandler:
                 opus_datas, text_index, tts_file = [], 0, None
                 try:
                     self.logger.bind(tag=TAG).debug("正在处理TTS任务...")
-                    tts_timeout = self.config.get("tts_timeout", 10)
+                    tts_timeout = int(self.config.get("tts_timeout", 10))
                     tts_file, text, text_index = future.result(timeout=tts_timeout)
                     if text is None or len(text) <= 0:
                         self.logger.bind(tag=TAG).error(

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

@@ -71,8 +71,8 @@ async def no_voice_close_connect(conn):
         conn.client_no_voice_last_time = time.time() * 1000
     else:
         no_voice_time = time.time() * 1000 - conn.client_no_voice_last_time
-        close_connection_no_voice_time = conn.config.get(
-            "close_connection_no_voice_time", 120
+        close_connection_no_voice_time = int(
+            conn.config.get("close_connection_no_voice_time", 120)
         )
         if (
             not conn.close_after_chat

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

@@ -58,7 +58,8 @@ class LLMProvider(LLMProviderBase):
                                 self.session_conversation_map[session_id] = (
                                     conversation_id  # 更新映射
                                 )
-                            if event.get("answer"):
+                            # 过滤 message_replace 事件，此事件会全量推一次
+                            if event.get("event") != "message_replace" and event.get("answer"):
                                 yield event["answer"]
                 elif self.mode == "workflows/run":
                     for line in r.iter_lines():
@@ -73,7 +74,8 @@ class LLMProvider(LLMProviderBase):
                     for line in r.iter_lines():
                         if line.startswith(b"data: "):
                             event = json.loads(line[6:])
-                            if event.get("answer"):
+                            # 过滤 message_replace 事件，此事件会全量推一次
+                            if event.get("event") != "message_replace" and event.get("answer"):
                                 yield event["answer"]
 
         except Exception as e:

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

@@ -89,19 +89,19 @@ class TTSProvider(TTSProviderBase):
         self.reference_audio = config.get("reference_audio", [])
         self.reference_text = config.get("reference_text", [])
         self.format = config.get("format", "wav")
-        self.channels = config.get("channels", 1)
-        self.rate = config.get("rate", 44100)
+        self.channels = int(config.get("channels", 1))
+        self.rate = int(config.get("rate", 44100))
         self.api_key = config.get("api_key", "YOUR_API_KEY")
         have_key = check_model_key("FishSpeech TTS", self.api_key)
         if not have_key:
             return
         self.normalize = config.get("normalize", True)
-        self.max_new_tokens = config.get("max_new_tokens", 1024)
-        self.chunk_length = config.get("chunk_length", 200)
-        self.top_p = config.get("top_p", 0.7)
-        self.repetition_penalty = config.get("repetition_penalty", 1.2)
-        self.temperature = config.get("temperature", 0.7)
-        self.streaming = config.get("streaming", False)
+        self.max_new_tokens = int(config.get("max_new_tokens", 1024))
+        self.chunk_length = int(config.get("chunk_length", 200))
+        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.use_memory_cache = config.get("use_memory_cache", "on")
         self.seed = config.get("seed")
         self.api_url = config.get("api_url", "http://127.0.0.1:8080/v1/tts")

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

@@ -10,6 +10,7 @@ from core.providers.tts.base import TTSProviderBase
 TAG = __name__
 logger = setup_logging()
 
+
 class TTSProvider(TTSProviderBase):
     def __init__(self, config, delete_audio_file):
         super().__init__(config, delete_audio_file)
@@ -18,23 +19,26 @@ class TTSProvider(TTSProviderBase):
         self.ref_audio_path = config.get("ref_audio_path")
         self.prompt_text = config.get("prompt_text")
         self.prompt_lang = config.get("prompt_lang", "zh")
-        self.top_k = config.get("top_k", 5)
-        self.top_p = config.get("top_p", 1)
-        self.temperature = config.get("temperature", 1)
+        self.top_k = int(config.get("top_k", 5))
+        self.top_p = float(config.get("top_p", 1))
+        self.temperature = float(config.get("temperature", 1))
         self.text_split_method = config.get("text_split_method", "cut0")
-        self.batch_size = config.get("batch_size", 1)
-        self.batch_threshold = config.get("batch_threshold", 0.75)
-        self.split_bucket = config.get("split_bucket", True)
-        self.return_fragment = config.get("return_fragment", False)
-        self.speed_factor = config.get("speed_factor", 1.0)
-        self.streaming_mode = config.get("streaming_mode", False)
-        self.seed = config.get("seed", -1)
-        self.parallel_infer = config.get("parallel_infer", True)
-        self.repetition_penalty = config.get("repetition_penalty", 1.35)
+        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.speed_factor = float(config.get("speed_factor", 1.0))
+        self.streaming_mode = bool(config.get("streaming_mode", False))
+        self.seed = int(config.get("seed", -1))
+        self.parallel_infer = bool(config.get("parallel_infer", True))
+        self.repetition_penalty = float(config.get("repetition_penalty", 1.35))
         self.aux_ref_audio_paths = config.get("aux_ref_audio_paths", [])
 
     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 = {
@@ -56,7 +60,7 @@ class TTSProvider(TTSProviderBase):
             "streaming_mode": self.streaming_mode,
             "seed": self.seed,
             "parallel_infer": self.parallel_infer,
-            "repetition_penalty": self.repetition_penalty
+            "repetition_penalty": self.repetition_penalty,
         }
 
         resp = requests.post(self.url, json=request_json)
@@ -64,4 +68,6 @@ class TTSProvider(TTSProviderBase):
             with open(output_file, "wb") as file:
                 file.write(resp.content)
         else:
-            logger.bind(tag=TAG).error(f"GPT_SoVITS_V2 TTS请求失败: {resp.status_code} - {resp.text}")
+            logger.bind(tag=TAG).error(
+                f"GPT_SoVITS_V2 TTS请求失败: {resp.status_code} - {resp.text}"
+            )

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

@@ -8,6 +8,7 @@ from core.providers.tts.base import TTSProviderBase
 TAG = __name__
 logger = setup_logging()
 
+
 class TTSProvider(TTSProviderBase):
     def __init__(self, config, delete_audio_file):
         super().__init__(config, delete_audio_file)
@@ -16,18 +17,20 @@ class TTSProvider(TTSProviderBase):
         self.prompt_text = config.get("prompt_text")
         self.prompt_language = config.get("prompt_language")
         self.text_language = config.get("text_language", "audo")
-        self.top_k = config.get("top_k", 15)
-        self.top_p = config.get("top_p", 1.0)
-        self.temperature = config.get("temperature", 1.0)
-        self.cut_punc = config.get("cut_punc","")
-        self.speed = config.get("speed", 1.0)
-        self.inp_refs = config.get("inp_refs",[])
-        self.sample_steps = config.get("sample_steps",32)
-        self.if_sr = config.get("if_sr",False)
-
+        self.top_k = int(config.get("top_k", 15))
+        self.top_p = float(config.get("top_p", 1.0))
+        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.sample_steps = int(config.get("sample_steps", 32))
+        self.if_sr = bool(config.get("if_sr", False))
 
     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_params = {
@@ -51,4 +54,6 @@ class TTSProvider(TTSProviderBase):
             with open(output_file, "wb") as file:
                 file.write(resp.content)
         else:
-            logger.bind(tag=TAG).error(f"GPT_SoVITS_V3 TTS请求失败: {resp.status_code} - {resp.text}")
+            logger.bind(tag=TAG).error(
+                f"GPT_SoVITS_V3 TTS请求失败: {resp.status_code} - {resp.text}"
+            )

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

@@ -21,7 +21,7 @@ class TTSProvider(TTSProviderBase):
         else:
             self.voice = config.get("voice", "alloy")
         self.response_format = "wav"
-        self.speed = config.get("speed", 1.0)
+        self.speed = float(config.get("speed", 1.0))
         self.output_file = config.get("output_dir", "tmp/")
         check_model_key("TTS", self.api_key)
 

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

@@ -16,7 +16,7 @@ class TTSProvider(TTSProviderBase):
             self.voice = config.get("voice")
         self.response_format = config.get("response_format")
         self.sample_rate = config.get("sample_rate")
-        self.speed = config.get("speed")
+        self.speed = float(config.get("speed"))
         self.gain = config.get("gain")
 
         self.host = "api.siliconflow.cn"

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

@@ -19,7 +19,7 @@ class TTSProvider(TTSProviderBase):
         if config.get("private_voice"):
             self.voice = config.get("private_voice")
         else:
-            self.voice = config.get("voice")
+            self.voice = int(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")

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

@@ -20,13 +20,13 @@ class TTSProvider(TTSProviderBase):
             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)
-        self.speed_factor = config.get("speed_factor", 1)
-        self.stream = config.get("stream", False)
+        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.output_file = config.get("output_dir")
-        self.pitch_factor = config.get("pitch_factor", 0)
+        self.pitch_factor = int(config.get("pitch_factor", 0))
         self.format = config.get("format", "mp3")
-        self.emotion = config.get("emotion", 1)
+        self.emotion = int(config.get("emotion", 1))
         self.header = {"Content-Type": "application/json"}
 
     def generate_filename(self, extension=".mp3"):

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

@@ -21,8 +21,8 @@ class VADProvider(VADProviderBase):
         (get_speech_timestamps, _, _, _, _) = self.utils
 
         self.decoder = opuslib_next.Decoder(16000, 1)
-        self.vad_threshold = config.get("threshold")
-        self.silence_threshold_ms = config.get("min_silence_duration_ms")
+        self.vad_threshold = float(config.get("threshold", 0.5))
+        self.silence_threshold_ms = int(config.get("min_silence_duration_ms", 1000))
 
     def is_vad(self, conn, opus_packet):
         try:

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

@@ -230,7 +230,7 @@ def initialize_modules(
         modules["tts"] = tts.create_instance(
             tts_type,
             config["TTS"][config["selected_module"]["TTS"]],
-            config["delete_audio"],
+            bool(config.get("delete_audio", True)),
         )
         logger.bind(tag=TAG).info(f"初始化组件: tts成功")
 
@@ -294,7 +294,7 @@ def initialize_modules(
         modules["asr"] = asr.create_instance(
             asr_type,
             config["ASR"][config["selected_module"]["ASR"]],
-            config["delete_audio"],
+            bool(config.get("delete_audio", True)),
         )
         logger.bind(tag=TAG).info(f"初始化组件: asr成功")
 

main/xiaozhi-server/core/websocket_server.py

@@ -25,7 +25,7 @@ class WebSocketServer:
     async def start(self):
         server_config = self.config["server"]
         host = server_config["ip"]
-        port = server_config["port"]
+        port = int(server_config.get("port", 8000))
 
         self.logger.bind(tag=TAG).info(
             "Server is running at ws://{}:{}/xiaozhi/v1/", get_local_ip(), port

main/xiaozhi-server/docker-compose_all.yml

@@ -1,25 +1,17 @@
 # Docker安装全模块
 
-# 1、安装mysql
-# |- 如果本机已经安装了MySQL，可以直接在数据库中创建名为`xiaozhi_esp32_server`的数据库。
-# |- 如果还没有MySQL，你可以通过docker安装mysql,执行以下一句话
-# |- docker run --name xiaozhi-esp32-server-db -e MYSQL_ROOT_PASSWORD=123456 -p 3306:3306 -e MYSQL_DATABASE=xiaozhi_esp32_server -e MYSQL_INITDB_ARGS="--character-set-server=utf8mb4 --collation-server=utf8mb4_unicode_ci" -d mysql:latest
-# |- 记得修改下方SPRING_DATASOURCE_DRUID_URL的IP，ip不能写127.0.0.1或localhost，否则容器无法访问，要写你电脑局域网ip
-
-# 2、安装redis
-# |- 如果本机已经安装了Redis，看一下你安装的redis端口、密码，然后修改下方redis的地址和端口
-# |- 如果还没有Redis，你可以通过docker安装redis,执行以下一句话
-# |- docker run --name xiaozhi-esp32-server-redis -d -p 6379:6379 redis
-# |- 记得修改SPRING_DATA_REDIS_HOST的IP，ip不能写127.0.0.1或localhost，否则容器无法访问，要写你电脑局域网ip
-
-
 version: '3'
 services:
   # Server模块
   xiaozhi-esp32-server:
     image: ghcr.nju.edu.cn/xinnan-tech/xiaozhi-esp32-server:server_latest
     container_name: xiaozhi-esp32-server
+    depends_on:
+      - xiaozhi-esp32-server-db
+      - xiaozhi-esp32-server-redis
     restart: always
+    networks:
+      - default
     ports:
       # ws服务端
       - "8000:8000"
@@ -38,14 +30,55 @@ services:
     image: ghcr.nju.edu.cn/xinnan-tech/xiaozhi-esp32-server:web_latest
     container_name: xiaozhi-esp32-server-web
     restart: always
+    networks:
+      - default
+    depends_on:
+      xiaozhi-esp32-server-db:
+        condition: service_healthy
+      xiaozhi-esp32-server-redis:
+        condition: service_healthy
     ports:
       # 智控台
       - "8002:8002"
     environment:
       - TZ=Asia/Shanghai
       ##记得改mysql和redis IP 密码
-      - SPRING_DATASOURCE_DRUID_URL=jdbc:mysql://192.168.1.25:3306/xiaozhi_esp32_server?useUnicode=true&characterEncoding=UTF-8&serverTimezone=Asia/Shanghai
+      - 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
-      - SPRING_DATA_REDIS_HOST=192.168.1.25
+      - SPRING_DATA_REDIS_HOST=xiaozhi-esp32-server-redis
       - SPRING_DATA_REDIS_PORT=6379
+  xiaozhi-esp32-server-db:
+    image: mysql:latest
+    container_name: xiaozhi-esp32-server-db
+    healthcheck:
+      test: [ "CMD", "mysqladmin" ,"ping", "-h", "localhost" ]
+      timeout: 45s
+      interval: 10s
+      retries: 10
+    restart: always
+    networks:
+      - default
+    expose:
+      - "3306:3306"
+    volumes:
+      - ./mysql/data:/var/lib/mysql
+    environment:
+      - TZ=Asia/Shanghai
+      - MYSQL_ROOT_PASSWORD=123456
+      - MYSQL_DATABASE=xiaozhi_esp32_server
+      - MYSQL_INITDB_ARGS="--character-set-server=utf8mb4 --collation-server=utf8mb4_unicode_ci"
+  xiaozhi-esp32-server-redis:
+    image: redis
+    expose:
+      - 6379
+    container_name: xiaozhi-esp32-server-redis
+    healthcheck:
+      test: ["CMD", "redis-cli", "ping"]
+      interval: 10s
+      timeout: 5s
+      retries: 3
+    networks:
+      - default
+networks:
+  default: