diff --git a/astrbot/core/config/i18n_utils.py b/astrbot/core/config/i18n_utils.py
index aa441c0c16..cb6b6429b5 100644
--- a/astrbot/core/config/i18n_utils.py
+++ b/astrbot/core/config/i18n_utils.py
@@ -42,6 +42,55 @@ def convert_to_i18n_keys(metadata: dict[str, Any]) -> dict[str, Any]:
         """
         result = {}
 
+        def convert_items(
+            group: str, section: str, items: dict[str, Any], prefix: str = ""
+        ) -> dict[str, Any]:
+            items_result: dict[str, Any] = {}
+
+            for field_key, field_data in items.items():
+                if not isinstance(field_data, dict):
+                    items_result[field_key] = field_data
+                    continue
+
+                field_name = field_key
+                field_path = f"{prefix}.{field_name}" if prefix else field_name
+
+                field_result = {
+                    key: value
+                    for key, value in field_data.items()
+                    if key not in {"description", "hint", "labels", "name"}
+                }
+
+                if "description" in field_data:
+                    field_result["description"] = (
+                        f"{group}.{section}.{field_path}.description"
+                    )
+                if "hint" in field_data:
+                    field_result["hint"] = f"{group}.{section}.{field_path}.hint"
+                if "labels" in field_data:
+                    field_result["labels"] = f"{group}.{section}.{field_path}.labels"
+                if "name" in field_data:
+                    field_result["name"] = f"{group}.{section}.{field_path}.name"
+
+                if "items" in field_data and isinstance(field_data["items"], dict):
+                    field_result["items"] = convert_items(
+                        group, section, field_data["items"], field_path
+                    )
+
+                if "template_schema" in field_data and isinstance(
+                    field_data["template_schema"], dict
+                ):
+                    field_result["template_schema"] = convert_items(
+                        group,
+                        section,
+                        field_data["template_schema"],
+                        f"{field_path}.template_schema",
+                    )
+
+                items_result[field_key] = field_result
+
+            return items_result
+
         for group_key, group_data in metadata.items():
             group_result = {
                 "name": f"{group_key}.name",
@@ -50,59 +99,19 @@ def convert_to_i18n_keys(metadata: dict[str, Any]) -> dict[str, Any]:
 
             for section_key, section_data in group_data.get("metadata", {}).items():
                 section_result = {
-                    "description": f"{group_key}.{section_key}.description",
-                    "type": section_data.get("type"),
+                    key: value
+                    for key, value in section_data.items()
+                    if key not in {"description", "hint", "labels", "name"}
                 }
+                section_result["description"] = f"{group_key}.{section_key}.description"
 
-                # 复制其他属性
-                for key in ["items", "condition", "_special", "invisible"]:
-                    if key in section_data:
-                        section_result[key] = section_data[key]
-
-                # 处理 hint
                 if "hint" in section_data:
                     section_result["hint"] = f"{group_key}.{section_key}.hint"
 
-                # 处理 items 中的字段
                 if "items" in section_data and isinstance(section_data["items"], dict):
-                    items_result = {}
-                    for field_key, field_data in section_data["items"].items():
-                        # 处理嵌套的点号字段名（如 provider_settings.enable）
-                        field_name = field_key
-
-                        field_result = {}
-
-                        # 复制基本属性
-                        for attr in [
-                            "type",
-                            "condition",
-                            "_special",
-                            "invisible",
-                            "options",
-                            "slider",
-                        ]:
-                            if attr in field_data:
-                                field_result[attr] = field_data[attr]
-
-                        # 转换文本属性为国际化键
-                        if "description" in field_data:
-                            field_result["description"] = (
-                                f"{group_key}.{section_key}.{field_name}.description"
-                            )
-
-                        if "hint" in field_data:
-                            field_result["hint"] = (
-                                f"{group_key}.{section_key}.{field_name}.hint"
-                            )
-
-                        if "labels" in field_data:
-                            field_result["labels"] = (
-                                f"{group_key}.{section_key}.{field_name}.labels"
-                            )
-
-                        items_result[field_key] = field_result
-
-                    section_result["items"] = items_result
+                    section_result["items"] = convert_items(
+                        group_key, section_key, section_data["items"]
+                    )
 
                 group_result["metadata"][section_key] = section_result
 
diff --git a/astrbot/dashboard/routes/config.py b/astrbot/dashboard/routes/config.py
index c5998682c8..e018d64755 100644
--- a/astrbot/dashboard/routes/config.py
+++ b/astrbot/dashboard/routes/config.py
@@ -1,4 +1,5 @@
 import asyncio
+import copy
 import inspect
 import os
 import traceback
@@ -407,8 +408,19 @@ async def update_provider_source(self):
         return Response().ok(message="更新 provider source 成功").__dict__
 
     async def get_provider_template(self):
+        provider_metadata = ConfigMetadataI18n.convert_to_i18n_keys(
+            {
+                "provider_group": {
+                    "metadata": {
+                        "provider": CONFIG_METADATA_2["provider_group"]["metadata"][
+                            "provider"
+                        ]
+                    }
+                }
+            }
+        )
         config_schema = {
-            "provider": CONFIG_METADATA_2["provider_group"]["metadata"]["provider"]
+            "provider": provider_metadata["provider_group"]["metadata"]["provider"]
         }
         data = {
             "config_schema": config_schema,
@@ -1278,11 +1290,24 @@ async def _register_platform_logo(self, platform, platform_default_tmpl):
 
     async def _get_astrbot_config(self):
         config = self.config
+        metadata = copy.deepcopy(CONFIG_METADATA_2)
+        platform_i18n = ConfigMetadataI18n.convert_to_i18n_keys(
+            {
+                "platform_group": {
+                    "metadata": {
+                        "platform": metadata["platform_group"]["metadata"]["platform"]
+                    }
+                }
+            }
+        )
+        metadata["platform_group"]["metadata"]["platform"] = platform_i18n[
+            "platform_group"
+        ]["metadata"]["platform"]
 
         # 平台适配器的默认配置模板注入
-        platform_default_tmpl = CONFIG_METADATA_2["platform_group"]["metadata"][
-            "platform"
-        ]["config_template"]
+        platform_default_tmpl = metadata["platform_group"]["metadata"]["platform"][
+            "config_template"
+        ]
 
         # 收集需要注册logo的平台
         logo_registration_tasks = []
@@ -1300,14 +1325,14 @@ async def _get_astrbot_config(self):
             await asyncio.gather(*logo_registration_tasks, return_exceptions=True)
 
         # 服务提供商的默认配置模板注入
-        provider_default_tmpl = CONFIG_METADATA_2["provider_group"]["metadata"][
-            "provider"
-        ]["config_template"]
+        provider_default_tmpl = metadata["provider_group"]["metadata"]["provider"][
+            "config_template"
+        ]
         for provider in provider_registry:
             if provider.default_config_tmpl:
                 provider_default_tmpl[provider.type] = provider.default_config_tmpl
 
-        return {"metadata": CONFIG_METADATA_2, "config": config}
+        return {"metadata": metadata, "config": config}
 
     async def _get_plugin_config(self, plugin_name: str):
         ret: dict = {"metadata": None, "config": None}
diff --git a/dashboard/src/components/platform/AddNewPlatform.vue b/dashboard/src/components/platform/AddNewPlatform.vue
index 118aa202a8..3be4d92f60 100644
--- a/dashboard/src/components/platform/AddNewPlatform.vue
+++ b/dashboard/src/components/platform/AddNewPlatform.vue
@@ -9,14 +9,14 @@
           </div>
           <div style="flex: 1;">
             <h3>
-              选择消息平台类别
+              {{ tm('createDialog.step1Title') }}
             </h3>
-            <small style="color: grey;">想把机器人接入到哪里？如 QQ、企业微信、飞书、Discord、Telegram 等。</small>
+            <small style="color: grey;">{{ tm('createDialog.step1Hint') }}</small>
             <div>
 
               <div v-if="!updatingMode">
                 <v-select v-model="selectedPlatformType" :items="Object.keys(platformTemplates)" item-title="name"
-                  item-value="name" label="消息平台类别" variant="outlined" rounded="md" dense hide-details class="mt-6"
+                  item-value="name" :label="tm('createDialog.platformTypeLabel')" variant="outlined" rounded="md" dense hide-details class="mt-6"
                   style="max-width: 30%; min-width: 300px;">
 
                   <template v-slot:item="{ props: itemProps, item }">
@@ -41,7 +41,7 @@
                 </div>
               </div>
               <div v-else>
-                <v-text-field label="消息平台类别" variant="outlined" rounded="md" dense hide-details class="mt-6"
+                <v-text-field :label="tm('createDialog.platformTypeLabel')" variant="outlined" rounded="md" dense hide-details class="mt-6"
                   style="max-width: 30%; min-width: 300px;" v-model="updatingPlatformConfig.type"
                   disabled></v-text-field>
                 <div class="mt-3">
@@ -65,13 +65,13 @@
               <div>
                 <div class="d-flex align-center">
                   <h3>
-                    配置文件
+                    {{ tm('createDialog.configFileTitle') }}
                   </h3>
                   <v-chip size="x-small" color="primary" variant="tonal" rounded="sm" class="ml-2"
-                    v-if="!updatingMode">可选</v-chip>
+                    v-if="!updatingMode">{{ tm('createDialog.optional') }}</v-chip>
                 </div>
-                <small style="color: grey;">想如何配置机器人？配置文件包含了聊天模型、人格、知识库、插件范围等丰富的机器人配置项。</small>
-                <small style="color: grey;" v-if="!updatingMode">默认使用默认配置文件 “default”。您也可以稍后配置。</small>
+                <small style="color: grey;">{{ tm('createDialog.configHint') }}</small>
+                <small style="color: grey;" v-if="!updatingMode">{{ tm('createDialog.configDefaultHint') }}</small>
               </div>
               <div>
                 <v-btn variant="plain" icon @click="toggleConfigSection" class="mt-2">
@@ -86,12 +86,12 @@
                 <v-radio-group class="mt-2" v-model="aBConfigRadioVal" hide-details="true">
                   <v-radio value="0">
                     <template v-slot:label>
-                      <span>使用现有配置文件</span>
+                      <span>{{ tm('createDialog.useExistingConfig') }}</span>
                     </template>
                   </v-radio>
                   <div class="d-flex align-center ml-10 my-2" v-if="aBConfigRadioVal === '0'">
                     <v-select v-model="selectedAbConfId" :items="configInfoList" item-title="name"
-                      item-value="id" label="选择配置文件" variant="outlined" rounded="md" dense hide-details
+                      item-value="id" :label="tm('createDialog.selectConfigLabel')" variant="outlined" rounded="md" dense hide-details
                       style="max-width: 30%; min-width: 200px;">
                     </v-select>
                     <v-btn icon variant="text" density="comfortable" class="ml-2"
@@ -99,10 +99,10 @@
                       <v-icon>mdi-arrow-top-right-thick</v-icon>
                     </v-btn>
                   </div>
-                  <v-radio value="1" label="创建新配置文件">
+                  <v-radio value="1" :label="tm('createDialog.createNewConfig')">
                   </v-radio>
                   <div class="d-flex align-center" v-if="aBConfigRadioVal === '1'">
-                    <v-text-field v-model="selectedAbConfId" label="新配置文件名称" variant="outlined" rounded="md" dense
+                    <v-text-field v-model="selectedAbConfId" :label="tm('createDialog.newConfigNameLabel')" variant="outlined" rounded="md" dense
                       hide-details style="max-width: 30%; min-width: 200px;" class="ml-10 my-2">
                     </v-text-field>
                   </div>
@@ -131,12 +131,12 @@
                     <v-progress-circular indeterminate color="primary"></v-progress-circular>
                   </div>
                   <div v-else-if="newConfigData && newConfigMetadata" class="config-preview-container">
-                    <h4 class="mb-3">使用新的配置文件</h4>
+                    <h4 class="mb-3">{{ tm('createDialog.newConfigTitle') }}</h4>
                     <AstrBotCoreConfigWrapper :metadata="newConfigMetadata" :config_data="newConfigData" />
                   </div>
                   <div v-else class="text-center py-4 text-grey">
                     <v-icon>mdi-information-outline</v-icon>
-                    <p class="mt-2">无法加载默认配置模板</p>
+                    <p class="mt-2">{{ tm('createDialog.newConfigLoadFailed') }}</p>
                   </div>
                 </div>
 
@@ -147,18 +147,18 @@
                   <div>
                     <v-btn v-if="isEditingRoutes" color="primary" variant="tonal" @click="addNewRoute" size="small">
                       <v-icon start>mdi-plus</v-icon>
-                      添加路由规则
+                      {{ tm('createDialog.addRouteRule') }}
                     </v-btn>
                   </div>
                   <v-btn :color="isEditingRoutes ? 'grey' : 'primary'" variant="tonal" size="small"
                     @click="toggleEditMode">
                     <v-icon start>{{ isEditingRoutes ? 'mdi-eye' : 'mdi-pencil' }}</v-icon>
-                    {{ isEditingRoutes ? '查看' : '编辑' }}
+                    {{ isEditingRoutes ? tm('createDialog.viewMode') : tm('createDialog.editMode') }}
                   </v-btn>
                 </div>
 
                 <v-data-table :headers="routeTableHeaders" :items="platformRoutes" item-value="umop"
-                  no-data-text="该平台暂无路由规则，将使用默认配置文件" hide-default-footer :items-per-page="-1" class="mt-2"
+                  :no-data-text="tm('createDialog.noRouteRules')" hide-default-footer :items-per-page="-1" class="mt-2"
                   variant="outlined">
 
                   <template v-slot:item.source="{ item }">
@@ -170,9 +170,9 @@
                       <small v-else>{{ getMessageTypeLabel(item.messageType) }}</small>
                       <small class="mx-1">:</small>
                       <v-text-field v-if="isEditingRoutes" v-model="item.sessionId" variant="outlined" density="compact"
-                        hide-details placeholder="会话ID或*">
+                        hide-details :placeholder="tm('createDialog.sessionIdPlaceholder')">
                       </v-text-field>
-                      <small v-else>{{ item.sessionId === '*' ? '全部会话' : item.sessionId }}</small>
+                      <small v-else>{{ item.sessionId === '*' ? tm('createDialog.allSessions') : item.sessionId }}</small>
                     </div>
                   </template>
 
@@ -191,7 +191,7 @@
                       </v-btn>
                     </div>
                     <small v-if="configInfoList.findIndex(c => c.id === item.configId) === -1" style="color: red;"
-                      class="ml-2">配置文件不存在</small>
+                      class="ml-2">{{ tm('createDialog.configMissing') }}</small>
                   </template>
 
                   <template v-slot:item.actions="{ item, index }">
@@ -211,8 +211,7 @@
                   </template>
 
                 </v-data-table>
-                <small class="ml-2 mt-2 d-block" style="color: grey">*消息下发时，根据会话来源按顺序从上到下匹配首个符合条件的配置文件。使用 * 表示匹配所有。使用 /sid 指令获取会话
-                  ID。全部不匹配时将使用默认配置文件。</small>
+                <small class="ml-2 mt-2 d-block" style="color: grey">{{ tm('createDialog.routeHint') }}</small>
               </div>
             </div>
 
@@ -266,10 +265,10 @@
       <v-card-actions class="px-4 pb-4">
         <v-spacer></v-spacer>
         <v-btn color="error" @click="handleOneBotEmptyTokenWarningDismiss(true)">
-          无视警告并继续创建
+          {{ tm('createDialog.warningContinue') }}
         </v-btn>
         <v-btn color="primary" @click="handleOneBotEmptyTokenWarningDismiss(false)">
-          重新修改
+          {{ tm('createDialog.warningEditAgain') }}
         </v-btn>
       </v-card-actions>
     </v-card>
@@ -286,9 +285,9 @@
     <v-card class="config-drawer-card" elevation="12">
       <div class="config-drawer-header">
         <div>
-          <span class="text-h6">配置文件管理</span>
+          <span class="text-h6">{{ tm('createDialog.configDrawerTitle') }}</span>
           <div v-if="configDrawerTargetId" class="text-caption text-grey">
-            ID: {{ configDrawerTargetId }}
+            {{ tm('createDialog.configDrawerIdLabel') }}: {{ configDrawerTargetId }}
           </div>
         </div>
         <v-btn icon variant="text" @click="closeConfigDrawer">
@@ -359,23 +358,9 @@ export default {
 
       // 平台配置文件表格（已弃用，改用 platformRoutes）
       platformConfigs: [],
-      configTableHeaders: [
-        { title: '与此实例关联的配置文件 ID', key: 'name', sortable: false },
-        { title: '在此实例下的应用范围', key: 'scope', sortable: false },
-      ],
 
       // 平台路由表
       platformRoutes: [],
-      routeTableHeaders: [
-        { title: '消息会话来源(消息类型:会话 ID)', key: 'source', sortable: false, width: '60%' },
-        { title: '使用配置文件', key: 'configId', sortable: false, width: '20%' },
-        { title: '操作', key: 'actions', sortable: false, align: 'center', width: '20%' },
-      ],
-      messageTypeOptions: [
-        { label: '全部消息', value: '*' },
-        { label: '群组消息(GroupMessage)', value: 'GroupMessage' },
-        { label: '私聊消息(FriendMessage)', value: 'FriendMessage' },
-      ],
       isEditingRoutes: false, // 编辑模式开关
 
       // ID冲突确认对话框
@@ -437,6 +422,26 @@ export default {
       }
 
       return false;
+    },
+    configTableHeaders() {
+      return [
+        { title: this.tm('createDialog.configTableHeaders.configId'), key: 'name', sortable: false },
+        { title: this.tm('createDialog.configTableHeaders.scope'), key: 'scope', sortable: false },
+      ];
+    },
+    routeTableHeaders() {
+      return [
+        { title: this.tm('createDialog.routeTableHeaders.source'), key: 'source', sortable: false, width: '60%' },
+        { title: this.tm('createDialog.routeTableHeaders.config'), key: 'configId', sortable: false, width: '20%' },
+        { title: this.tm('createDialog.routeTableHeaders.actions'), key: 'actions', sortable: false, align: 'center', width: '20%' },
+      ];
+    },
+    messageTypeOptions() {
+      return [
+        { label: this.tm('createDialog.messageTypeOptions.all'), value: '*' },
+        { label: this.tm('createDialog.messageTypeOptions.group'), value: 'GroupMessage' },
+        { label: this.tm('createDialog.messageTypeOptions.friend'), value: 'FriendMessage' },
+      ];
     }
   },
   watch: {
@@ -603,7 +608,7 @@ export default {
       const targetId = configId || 'default';
 
       if (configId && this.configInfoList.findIndex(c => c.id === configId) === -1) {
-        this.showError('目标配置文件不存在，已打开配置页面以便检查。');
+        this.showError(this.tm('messages.configNotFoundOpenConfig'));
       }
 
       this.configDrawerTargetId = targetId;
@@ -637,7 +642,7 @@ export default {
       const id = this.originalUpdatingPlatformId || this.updatingPlatformConfig.id;
       if (!id) {
         this.loading = false;
-        this.showError('更新失败，缺少平台 ID。');
+        this.showError(this.tm('messages.updateMissingPlatformId'));
         return;
       }
 
@@ -655,7 +660,7 @@ export default {
         })
 
         if (resp.data.status === 'error') {
-          throw new Error(resp.data.message || '平台更新失败');
+          throw new Error(resp.data.message || this.tm('messages.platformUpdateFailed'));
         }
         
         // 同时更新路由表
@@ -665,7 +670,7 @@ export default {
         this.showDialog = false;
         this.resetForm();
         this.$emit('refresh-config');
-        this.showSuccess('更新成功');
+        this.showSuccess(this.tm('messages.updateSuccess'));
       } catch (err) {
         this.loading = false;
         this.showError(err.response?.data?.message || err.message);
@@ -710,7 +715,7 @@ export default {
         this.showDialog = false;
         this.resetForm();
         this.$emit('refresh-config');
-        this.showSuccess(res.data.message || '平台添加成功，配置文件已更新');
+        this.showSuccess(res.data.message || this.tm('messages.addSuccessWithConfig'));
       } catch (err) {
         this.loading = false;
         this.showError(err.response?.data?.message || err.message);
@@ -738,7 +743,7 @@ export default {
       }
 
       if (!configId) {
-        throw new Error('无法获取配置文件ID');
+        throw new Error(this.tm('messages.configIdMissing'));
       }
 
       // 第二步：统一更新路由表
@@ -755,7 +760,8 @@ export default {
         console.log(`成功更新路由表: ${umop} -> ${configId}`);
       } catch (err) {
         console.error('更新路由表失败:', err);
-        throw new Error(`更新路由表失败: ${err.response?.data?.message || err.message}`);
+        const errorMessage = err.response?.data?.message || err.message;
+        throw new Error(this.tm('messages.routingUpdateFailed', { message: errorMessage }));
       }
     },
 
@@ -778,7 +784,8 @@ export default {
         return newConfigId;
       } catch (err) {
         console.error('创建新配置文件失败:', err);
-        throw new Error(`创建新配置文件失败: ${err.response?.data?.message || err.message}`);
+        const errorMessage = err.response?.data?.message || err.message;
+        throw new Error(this.tm('messages.createConfigFailed', { message: errorMessage }));
       }
     },
 
@@ -922,7 +929,7 @@ export default {
       const newPlatformId = this.updatingPlatformConfig?.id || originalPlatformId;
 
       if (!originalPlatformId && !newPlatformId) {
-        throw new Error('无法获取平台 ID');
+        throw new Error(this.tm('messages.platformIdMissing'));
       }
 
       try {
@@ -958,7 +965,8 @@ export default {
         });
       } catch (err) {
         console.error('保存路由表失败:', err);
-        throw new Error(`保存路由表失败: ${err.response?.data?.message || err.message}`);
+        const errorMessage = err.response?.data?.message || err.message;
+        throw new Error(this.tm('messages.routingSaveFailed', { message: errorMessage }));
       }
     },
 
@@ -987,10 +995,10 @@ export default {
     // 获取消息类型标签
     getMessageTypeLabel(messageType) {
       const typeMap = {
-        '*': '全部消息',
-        '': '全部消息',
-        'GroupMessage': '群组消息',
-        'FriendMessage': '私聊消息'
+        '*': this.tm('createDialog.messageTypeLabels.all'),
+        '': this.tm('createDialog.messageTypeLabels.all'),
+        'GroupMessage': this.tm('createDialog.messageTypeLabels.group'),
+        'FriendMessage': this.tm('createDialog.messageTypeLabels.friend')
       };
       return typeMap[messageType] || messageType;
     },
diff --git a/dashboard/src/components/provider/ProviderSourcesPanel.vue b/dashboard/src/components/provider/ProviderSourcesPanel.vue
index 6f65af67b2..adca108325 100644
--- a/dashboard/src/components/provider/ProviderSourcesPanel.vue
+++ b/dashboard/src/components/provider/ProviderSourcesPanel.vue
@@ -14,7 +14,7 @@
             rounded="xl"
             size="small"
           >
-            新增
+            {{ tm('providerSources.add') }}
           </v-btn>
         </template>
         <v-list density="compact">
diff --git a/dashboard/src/components/shared/AstrBotConfig.vue b/dashboard/src/components/shared/AstrBotConfig.vue
index 22dc03807e..12cb0bee1c 100644
--- a/dashboard/src/components/shared/AstrBotConfig.vue
+++ b/dashboard/src/components/shared/AstrBotConfig.vue
@@ -3,7 +3,7 @@ import { VueMonacoEditor } from '@guolao/vue-monaco-editor'
 import { ref, computed } from 'vue'
 import ConfigItemRenderer from './ConfigItemRenderer.vue'
 import TemplateListEditor from './TemplateListEditor.vue'
-import { useI18n } from '@/i18n/composables'
+import { useI18n, useModuleI18n } from '@/i18n/composables'
 import axios from 'axios'
 import { useToast } from '@/utils/toast'
 
@@ -35,6 +35,12 @@ const props = defineProps({
 })
 
 const { t } = useI18n()
+const { tm, getRaw } = useModuleI18n('features/config-metadata')
+
+const translateIfKey = (value) => {
+  if (!value || typeof value !== 'string') return value
+  return getRaw(value) ? tm(value) : value
+}
 
 const filteredIterable = computed(() => {
   if (!props.iterable) return {}
@@ -134,11 +140,11 @@ function hasVisibleItemsAfter(items, currentIndex) {
 <template>
   <div class="config-section" v-if="iterable && metadata[metadataKey]?.type === 'object'">
     <v-list-item-title class="config-title">
-      {{ metadata[metadataKey]?.description }} <span class="metadata-key">({{ metadataKey }})</span>
+      {{ translateIfKey(metadata[metadataKey]?.description) }} <span class="metadata-key">({{ metadataKey }})</span>
     </v-list-item-title>
     <v-list-item-subtitle class="config-hint">
       <span v-if="metadata[metadataKey]?.obvious_hint && metadata[metadataKey]?.hint" class="important-hint">‼️</span>
-      {{ metadata[metadataKey]?.hint }}
+      {{ translateIfKey(metadata[metadataKey]?.hint) }}
     </v-list-item-subtitle>
   </div>
 
@@ -180,14 +186,14 @@ function hasVisibleItemsAfter(items, currentIndex) {
             <div class="config-section mb-2">
               <v-list-item-title class="config-title">
                 <span v-if="metadata[metadataKey].items[key]?.description">
-                  {{ metadata[metadataKey].items[key]?.description }}
+                  {{ translateIfKey(metadata[metadataKey].items[key]?.description) }}
                   <span class="property-key">({{ key }})</span>
                 </span>
                 <span v-else>{{ key }}</span>
               </v-list-item-title>
               <v-list-item-subtitle class="config-hint">
                 <span v-if="metadata[metadataKey].items[key]?.obvious_hint && metadata[metadataKey].items[key]?.hint" class="important-hint">‼️</span>
-                {{ metadata[metadataKey].items[key]?.hint }}
+                {{ translateIfKey(metadata[metadataKey].items[key]?.hint) }}
               </v-list-item-subtitle>
             </div>
             <TemplateListEditor
@@ -205,7 +211,7 @@ function hasVisibleItemsAfter(items, currentIndex) {
               <v-list-item density="compact">
                 <v-list-item-title class="property-name">
                   <span v-if="metadata[metadataKey].items[key]?.description">
-                    {{ metadata[metadataKey].items[key]?.description }}
+                    {{ translateIfKey(metadata[metadataKey].items[key]?.description) }}
                     <span class="property-key">({{ key }})</span>
                   </span>
                   <span v-else>{{ key }}</span>
@@ -214,7 +220,7 @@ function hasVisibleItemsAfter(items, currentIndex) {
                 <v-list-item-subtitle class="property-hint">
                   <span v-if="metadata[metadataKey].items[key]?.obvious_hint && metadata[metadataKey].items[key]?.hint"
                         class="important-hint">‼️</span>
-                  {{ metadata[metadataKey].items[key]?.hint }}
+                  {{ translateIfKey(metadata[metadataKey].items[key]?.hint) }}
                 </v-list-item-subtitle>
               </v-list-item>
             </v-col>
diff --git a/dashboard/src/composables/useProviderSources.ts b/dashboard/src/composables/useProviderSources.ts
index 07ac5aa150..dc573818ab 100644
--- a/dashboard/src/composables/useProviderSources.ts
+++ b/dashboard/src/composables/useProviderSources.ts
@@ -59,14 +59,14 @@ export function useProviderSources(options: UseProviderSourcesOptions) {
 
   let suppressSourceWatch = false
 
-  const providerTypes = [
+  const providerTypes = computed(() => [
     { value: 'chat_completion', label: tm('providers.tabs.chatCompletion'), icon: 'mdi-message-text' },
     { value: 'agent_runner', label: tm('providers.tabs.agentRunner'), icon: 'mdi-robot' },
     { value: 'speech_to_text', label: tm('providers.tabs.speechToText'), icon: 'mdi-microphone-message' },
     { value: 'text_to_speech', label: tm('providers.tabs.textToSpeech'), icon: 'mdi-volume-high' },
     { value: 'embedding', label: tm('providers.tabs.embedding'), icon: 'mdi-code-json' },
     { value: 'rerank', label: tm('providers.tabs.rerank'), icon: 'mdi-compare-vertical' }
-  ]
+  ])
 
   // ===== Computed =====
   const availableSourceTypes = computed(() => {
diff --git a/dashboard/src/i18n/locales/en-US/features/config-metadata.json b/dashboard/src/i18n/locales/en-US/features/config-metadata.json
index 9b4c4e3049..b93ba5374b 100644
--- a/dashboard/src/i18n/locales/en-US/features/config-metadata.json
+++ b/dashboard/src/i18n/locales/en-US/features/config-metadata.json
@@ -290,6 +290,235 @@
   },
   "platform_group": {
     "name": "Platform",
+    "platform": {
+      "description": "Message Platform Adapters",
+      "active_send_mode": {
+        "description": "Use Proactive Send API"
+      },
+      "appid": {
+        "description": "App ID",
+        "hint": "Required. App ID for the QQ Official Bot platform. See the docs for how to obtain it."
+      },
+      "callback_server_host": {
+        "description": "Callback Server Host",
+        "hint": "Callback server host. Leave empty to disable the callback server."
+      },
+      "card_template_id": {
+        "description": "Card Template ID",
+        "hint": "Optional. DingTalk interactive card template ID. When enabled, streaming replies will use interactive cards."
+      },
+      "discord_activity_name": {
+        "description": "Discord Activity Name",
+        "hint": "Optional Discord activity name. Leave empty to disable."
+      },
+      "discord_command_register": {
+        "description": "Auto-register plugin commands as Discord slash commands"
+      },
+      "discord_proxy": {
+        "description": "Discord Proxy URL",
+        "hint": "Optional proxy URL: http://ip:port"
+      },
+      "discord_token": {
+        "description": "Discord Bot Token",
+        "hint": "Enter your Discord Bot Token here."
+      },
+      "enable": {
+        "description": "Enable",
+        "hint": "Whether to enable this adapter. Disabled adapters will not receive messages."
+      },
+      "enable_group_c2c": {
+        "description": "Enable Message List Private Chat",
+        "hint": "When enabled, the bot can receive private chats from QQ message list. You may need to add the bot as a friend by scanning a QR code in the QQ bot platform. See docs."
+      },
+      "enable_guild_direct_message": {
+        "description": "Enable Guild Direct Messages",
+        "hint": "When enabled, the bot can receive guild direct messages."
+      },
+      "id": {
+        "description": "Bot Name",
+        "hint": "Bot name"
+      },
+      "is_sandbox": {
+        "description": "Sandbox Mode"
+      },
+      "kf_name": {
+        "description": "WeChat Customer Service Account Name",
+        "hint": "Optional. Customer service account name (not ID). Get it at https://kf.weixin.qq.com/kf/frame#/accounts"
+      },
+      "lark_bot_name": {
+        "description": "Lark Bot Name",
+        "hint": "Must be correct; otherwise @ mentions will not wake the bot and only prefix wake will work."
+      },
+      "lark_connection_mode": {
+        "description": "Subscription Mode",
+        "labels": [
+          "Long Connection Mode",
+          "Webhook Server Mode"
+        ]
+      },
+      "lark_encrypt_key": {
+        "description": "Encrypt Key",
+        "hint": "Encryption key for decrypting Lark callback data."
+      },
+      "lark_verification_token": {
+        "description": "Verification Token",
+        "hint": "Token for verifying Lark callback requests."
+      },
+      "misskey_allow_insecure_downloads": {
+        "description": "Allow Insecure Downloads (Disable SSL Verification)",
+        "hint": "If remote servers have certificate issues, SSL verification will be disabled as a fallback. Use only when necessary due to security risks."
+      },
+      "misskey_default_visibility": {
+        "description": "Default Post Visibility",
+        "hint": "Default visibility for bot posts. public: public, home: home timeline, followers: followers only."
+      },
+      "misskey_download_chunk_size": {
+        "description": "Stream Download Chunk Size (bytes)",
+        "hint": "Bytes read per chunk during streaming download and MD5 calculation. Too small increases overhead; too large uses more memory."
+      },
+      "misskey_download_timeout": {
+        "description": "Remote Download Timeout (seconds)",
+        "hint": "Timeout for downloading remote files (seconds), used when falling back to local upload."
+      },
+      "misskey_enable_chat": {
+        "description": "Enable Chat Message Responses",
+        "hint": "When enabled, the bot listens and responds to private chat messages."
+      },
+      "misskey_enable_file_upload": {
+        "description": "Enable File Upload to Misskey",
+        "hint": "When enabled, the adapter uploads files in message chains to Misskey. URL files try server-side upload first; if async upload fails, it falls back to local download and upload."
+      },
+      "misskey_instance_url": {
+        "description": "Misskey Instance URL",
+        "hint": "e.g. https://misskey.example. The Misskey instance where the bot account lives."
+      },
+      "misskey_local_only": {
+        "description": "Local Only (No Federation)",
+        "hint": "When enabled, bot posts are visible only on this instance and are not federated."
+      },
+      "misskey_max_download_bytes": {
+        "description": "Max Download Size (bytes)",
+        "hint": "To limit download size to prevent OOM, set the maximum bytes; empty or null means no limit."
+      },
+      "misskey_token": {
+        "description": "Misskey Access Token",
+        "hint": "API access token generated in the connection service settings."
+      },
+      "misskey_upload_concurrency": {
+        "description": "Upload Concurrency Limit",
+        "hint": "Max number of concurrent upload tasks (integer, default 3)."
+      },
+      "misskey_upload_folder": {
+        "description": "Target Drive Folder ID",
+        "hint": "Optional: ID of the target folder in Misskey drive. Leave empty to use the root folder."
+      },
+      "port": {
+        "description": "Callback Server Port",
+        "hint": "Callback server port. Leave empty to disable the callback server."
+      },
+      "satori_api_base_url": {
+        "description": "Satori API Endpoint",
+        "hint": "Base URL for the Satori API."
+      },
+      "satori_auto_reconnect": {
+        "description": "Enable Auto Reconnect",
+        "hint": "Automatically reconnect the WebSocket when disconnected."
+      },
+      "satori_endpoint": {
+        "description": "Satori WebSocket Endpoint",
+        "hint": "WebSocket endpoint for Satori events."
+      },
+      "satori_heartbeat_interval": {
+        "description": "Satori Heartbeat Interval",
+        "hint": "Interval in seconds between heartbeat messages."
+      },
+      "satori_reconnect_delay": {
+        "description": "Satori Reconnect Delay",
+        "hint": "Delay before attempting to reconnect (seconds)."
+      },
+      "satori_token": {
+        "description": "Satori Token",
+        "hint": "Token for Satori API authentication."
+      },
+      "secret": {
+        "description": "Secret",
+        "hint": "Required."
+      },
+      "slack_connection_mode": {
+        "description": "Slack Connection Mode",
+        "hint": "The connection mode for Slack. `webhook` uses a webhook server, `socket` uses Slack's Socket Mode."
+      },
+      "slack_webhook_host": {
+        "description": "Slack Webhook Host",
+        "hint": "Only valid when Slack connection mode is `webhook`."
+      },
+      "slack_webhook_path": {
+        "description": "Slack Webhook Path",
+        "hint": "Only valid when Slack connection mode is `webhook`."
+      },
+      "slack_webhook_port": {
+        "description": "Slack Webhook Port",
+        "hint": "Only valid when Slack connection mode is `webhook`."
+      },
+      "telegram_command_auto_refresh": {
+        "description": "Telegram Command Auto Refresh",
+        "hint": "When enabled, AstrBot automatically refreshes Telegram commands at runtime. (Setting this alone has no effect)"
+      },
+      "telegram_command_register": {
+        "description": "Telegram Command Registration",
+        "hint": "When enabled, AstrBot automatically registers Telegram commands."
+      },
+      "telegram_command_register_interval": {
+        "description": "Telegram Command Auto Refresh Interval",
+        "hint": "Telegram command auto-refresh interval in seconds."
+      },
+      "telegram_token": {
+        "description": "Bot Token",
+        "hint": "If you are in mainland China, set a proxy or change api_base in Other Settings."
+      },
+      "type": {
+        "description": "Adapter Type"
+      },
+      "unified_webhook_mode": {
+        "description": "Unified Webhook Mode",
+        "hint": "When enabled, use AstrBot unified webhook entry without opening a separate port. Callback URL is /api/platform/webhook/{webhook_uuid}."
+      },
+      "webhook_uuid": {
+        "description": "Webhook UUID",
+        "hint": "Unique identifier for unified webhook mode; generated when creating the platform."
+      },
+      "wecom_ai_bot_name": {
+        "description": "WeCom AI Bot Name",
+        "hint": "Must be correct; otherwise some commands won't work."
+      },
+      "wecomaibot_friend_message_welcome_text": {
+        "description": "WeCom AI Bot DM Welcome Message",
+        "hint": "When a user enters a DM session on that day, reply with a welcome message. Leave empty to disable."
+      },
+      "wecomaibot_init_respond_text": {
+        "description": "WeCom AI Bot Initial Response Text",
+        "hint": "First reply when the bot receives a message. Leave empty to use default."
+      },
+      "wpp_active_message_poll": {
+        "description": "Enable Proactive Message Polling",
+        "hint": "Only enable if WeChat messages are not syncing to AstrBot on time. Disabled by default."
+      },
+      "wpp_active_message_poll_interval": {
+        "description": "Proactive Message Poll Interval",
+        "hint": "Interval in seconds, default 3, should not exceed 60 or it may be considered old messages."
+      },
+      "ws_reverse_host": {
+        "description": "Reverse WebSocket Host",
+        "hint": "AstrBot acts as the server."
+      },
+      "ws_reverse_port": {
+        "description": "Reverse WebSocket Port"
+      },
+      "ws_reverse_token": {
+        "description": "Reverse WebSocket Token",
+        "hint": "Reverse WebSocket token. If not set, token verification is disabled."
+      }
+    },
     "general": {
       "description": "General",
       "admins_id": {
@@ -615,6 +844,443 @@
       }
     }
   },
+  "provider_group": {
+    "provider": {
+      "genie_onnx_model_dir": {
+        "description": "ONNX Model Directory",
+        "hint": "The directory path containing the ONNX model files"
+      },
+      "genie_language": {
+        "description": "Language"
+      },
+      "xai_native_search": {
+        "description": "Enable native search",
+        "hint": "When enabled, uses xAI Chat Completions native Live Search for web queries (billed on demand). Only applies to xAI providers."
+      },
+      "rerank_api_base": {
+        "description": "Rerank Model API Base URL",
+        "hint": "AstrBot appends /v1/rerank to the request URL."
+      },
+      "rerank_api_key": {
+        "description": "API Key",
+        "hint": "Leave empty if no API key is required."
+      },
+      "rerank_model": {
+        "description": "Rerank model name"
+      },
+      "return_documents": {
+        "description": "Return source documents in rerank results",
+        "hint": "Default is false to reduce network overhead."
+      },
+      "instruct": {
+        "description": "Custom rerank task description",
+        "hint": "Only effective for qwen3-rerank models. Recommended to write in English."
+      },
+      "launch_model_if_not_running": {
+        "description": "Auto-start model if not running",
+        "hint": "If the model is not running in Xinference, attempt to start it automatically. Recommended to disable in production."
+      },
+      "modalities": {
+        "description": "Model capabilities",
+        "hint": "Modalities supported by the model. If the model does not support images, uncheck image.",
+        "labels": [
+          "Text",
+          "Image",
+          "Tool use"
+        ]
+      },
+      "custom_headers": {
+        "description": "Custom request headers",
+        "hint": "Key/value pairs added here are merged into the OpenAI SDK default_headers for custom HTTP headers. Values must be strings."
+      },
+      "custom_extra_body": {
+        "description": "Custom request body parameters",
+        "hint": "Add extra parameters to requests, such as temperature, top_p, max_tokens, etc.",
+        "template_schema": {
+          "temperature": {
+            "description": "Temperature",
+            "hint": "Controls randomness, typically 0-2. Higher is more random.",
+            "name": "Temperature"
+          },
+          "top_p": {
+            "description": "Top-p sampling",
+            "hint": "Nucleus sampling parameter, usually 0-1. Controls probability mass considered.",
+            "name": "Top-p"
+          },
+          "max_tokens": {
+            "description": "Max tokens",
+            "hint": "Maximum number of generated tokens.",
+            "name": "Max Tokens"
+          }
+        }
+      },
+      "gpt_weights_path": {
+        "description": "GPT model file path",
+        "hint": "The .ckpt file. Use an absolute path without quotes. Leave empty to use the GPT_SoVITS built-in SoVITS model (recommended to change defaults in GPT_SoVITS)."
+      },
+      "sovits_weights_path": {
+        "description": "SoVITS model file path",
+        "hint": "The .pth file. Use an absolute path without quotes. Leave empty to use the GPT_SoVITS built-in SoVITS model (recommended to change defaults in GPT_SoVITS)."
+      },
+      "gsv_default_parms": {
+        "description": "GPT_SoVITS default parameters",
+        "hint": "Reference audio file path and text are required; other parameters are optional.",
+        "gsv_ref_audio_path": {
+          "description": "Reference audio file path",
+          "hint": "Required! Use an absolute path without quotes."
+        },
+        "gsv_prompt_text": {
+          "description": "Reference audio text",
+          "hint": "Required! Provide the transcript of the reference audio."
+        },
+        "gsv_prompt_lang": {
+          "description": "Reference audio text language",
+          "hint": "Language of the reference audio text; default is Chinese."
+        },
+        "gsv_aux_ref_audio_paths": {
+          "description": "Auxiliary reference audio file paths",
+          "hint": "Auxiliary reference audio files; optional."
+        },
+        "gsv_text_lang": {
+          "description": "Text language",
+          "hint": "Default is Chinese."
+        },
+        "gsv_top_k": {
+          "description": "Speech diversity",
+          "hint": ""
+        },
+        "gsv_top_p": {
+          "description": "Nucleus sampling threshold",
+          "hint": ""
+        },
+        "gsv_temperature": {
+          "description": "Speech randomness",
+          "hint": ""
+        },
+        "gsv_text_split_method": {
+          "description": "Text splitting method",
+          "hint": "Options: `cut0` no split, `cut1` split every 4 sentences, `cut2` split every 50 chars, `cut3` split by Chinese period, `cut4` split by English period, `cut5` split by punctuation."
+        },
+        "gsv_batch_size": {
+          "description": "Batch size",
+          "hint": ""
+        },
+        "gsv_batch_threshold": {
+          "description": "Batch threshold",
+          "hint": ""
+        },
+        "gsv_split_bucket": {
+          "description": "Split text into buckets for parallel processing",
+          "hint": ""
+        },
+        "gsv_speed_factor": {
+          "description": "Speech playback speed",
+          "hint": "1 is the original speed."
+        },
+        "gsv_fragment_interval": {
+          "description": "Interval between speech segments",
+          "hint": ""
+        },
+        "gsv_streaming_mode": {
+          "description": "Enable streaming mode",
+          "hint": ""
+        },
+        "gsv_seed": {
+          "description": "Random seed",
+          "hint": "For reproducible results."
+        },
+        "gsv_parallel_infer": {
+          "description": "Run inference in parallel",
+          "hint": ""
+        },
+        "gsv_repetition_penalty": {
+          "description": "Repetition penalty",
+          "hint": ""
+        },
+        "gsv_media_type": {
+          "description": "Output media type",
+          "hint": "Recommended: wav"
+        }
+      },
+      "embedding_dimensions": {
+        "description": "Embedding dimensions",
+        "hint": "Embedding vector dimensions. May need adjustment per model; see model documentation. This must be correct or the vector database will not work."
+      },
+      "embedding_model": {
+        "description": "Embedding model",
+        "hint": "Embedding model name."
+      },
+      "embedding_api_key": {
+        "description": "API Key"
+      },
+      "embedding_api_base": {
+        "description": "API Base URL"
+      },
+      "volcengine_cluster": {
+        "description": "Volcengine cluster",
+        "hint": "For voice cloning models, choose volcano_icl or volcano_icl_concurr; default is volcano_tts."
+      },
+      "volcengine_voice_type": {
+        "description": "Volcengine voice",
+        "hint": "Enter voice id (Voice_type)."
+      },
+      "volcengine_speed_ratio": {
+        "description": "Speech rate",
+        "hint": "Speech rate, range 0.2 to 3.0, default 1.0."
+      },
+      "volcengine_volume_ratio": {
+        "description": "Volume",
+        "hint": "Volume, range 0.0 to 2.0, default 1.0."
+      },
+      "azure_tts_voice": {
+        "description": "Voice style",
+        "hint": "API voice name"
+      },
+      "azure_tts_style": {
+        "description": "Style",
+        "hint": "A voice-specific speaking style. Can express emotions like happy, sympathetic, and calm."
+      },
+      "azure_tts_role": {
+        "description": "Role (optional)",
+        "hint": "Speaking role-play. The voice can emulate different ages and genders without changing the voice name. For example, a male voice can raise pitch to simulate a female voice, but the voice name does not change. If the role is missing or unsupported, this attribute is ignored."
+      },
+      "azure_tts_rate": {
+        "description": "Speech rate",
+        "hint": "Controls speaking rate. You can apply the rate at word or sentence level. Rate should be 0.5x to 2x of original audio."
+      },
+      "azure_tts_volume": {
+        "description": "Speech volume",
+        "hint": "Controls volume level. You can apply changes at sentence level. Use 0.0 to 100.0 (quiet to loud, e.g., 75). Default is 100.0."
+      },
+      "azure_tts_region": {
+        "description": "API region",
+        "hint": "Region where Azure TTS processes data. See https://learn.microsoft.com/zh-cn/azure/ai-services/speech-service/regions"
+      },
+      "azure_tts_subscription_key": {
+        "description": "Service subscription key",
+        "hint": "Azure TTS subscription key (not a token)."
+      },
+      "dashscope_tts_voice": {
+        "description": "Voice"
+      },
+      "gm_resp_image_modal": {
+        "description": "Enable image modality",
+        "hint": "When enabled, responses can include images. Requires model support or it will error. See the Google Gemini website for supported models. Tip: if you need image generation, disable the `Enable member recognition` setting for better results."
+      },
+      "gm_native_search": {
+        "description": "Enable native search",
+        "hint": "When enabled, all function tools are disabled. Check official docs for free quota limits."
+      },
+      "gm_native_coderunner": {
+        "description": "Enable native code runner",
+        "hint": "When enabled, all function tools are disabled."
+      },
+      "gm_url_context": {
+        "description": "Enable URL context",
+        "hint": "When enabled, all function tools are disabled."
+      },
+      "gm_safety_settings": {
+        "description": "Safety filters",
+        "hint": "Set the safety filtering level for model input. Levels: NONE (no blocking), HIGH (block high risk), MEDIUM_AND_ABOVE (block medium risk and above), LOW_AND_ABOVE (block low risk and above). See Gemini API docs.",
+        "harassment": {
+          "description": "Harassment",
+          "hint": "Negative or harmful comments"
+        },
+        "hate_speech": {
+          "description": "Hate speech",
+          "hint": "Rude, disrespectful, or profane content"
+        },
+        "sexually_explicit": {
+          "description": "Sexually explicit content",
+          "hint": "References to sexual acts or other obscene content"
+        },
+        "dangerous_content": {
+          "description": "Dangerous content",
+          "hint": "Content that promotes, encourages, or assists harmful behavior"
+        }
+      },
+      "gm_thinking_config": {
+        "description": "Thinking Config",
+        "budget": {
+          "description": "Thinking Budget",
+          "hint": "Guides the model on the specific number of thinking tokens to use for reasoning. See: https://ai.google.dev/gemini-api/docs/thinking#set-budget"
+        },
+        "level": {
+          "description": "Thinking Level",
+          "hint": "Recommended for Gemini 3 models and onwards, lets you control reasoning behavior.See: https://ai.google.dev/gemini-api/docs/thinking#thinking-levels"
+        }
+      },
+      "anth_thinking_config": {
+        "description": "Thinking Config",
+        "budget": {
+          "description": "Thinking Budget",
+          "hint": "Anthropic thinking.budget_tokens param. Must >= 1024. See: https://platform.claude.com/docs/en/build-with-claude/extended-thinking"
+        }
+      },
+      "minimax-group-id": {
+        "description": "User group",
+        "hint": "Visible in Account Management -> Basic Info."
+      },
+      "minimax-langboost": {
+        "description": "Target language/dialect",
+        "hint": "Enhances recognition for specified languages/dialects and improves speech performance in those scenarios."
+      },
+      "minimax-voice-speed": {
+        "description": "Speech rate",
+        "hint": "Speech speed for synthesis, range [0.5, 2], default 1.0. Higher is faster."
+      },
+      "minimax-voice-vol": {
+        "description": "Volume",
+        "hint": "Volume for synthesis, range (0, 10], default 1.0. Higher is louder."
+      },
+      "minimax-voice-pitch": {
+        "description": "Pitch",
+        "hint": "Pitch for synthesis, range [-12, 12], default 0."
+      },
+      "minimax-is-timber-weight": {
+        "description": "Enable mixed voices",
+        "hint": "Enable mixing up to four voices with custom weights. When enabled, single voice settings are ignored."
+      },
+      "minimax-timber-weight": {
+        "description": "Mixed voices",
+        "hint": "Mixed voices and their weights. Up to four voices, integer weights in [1, 100]. Get presets and templates from the official API TTS debug console. Must be a JSON string; check the console to confirm parsing. See defaults and the official code preview for structure."
+      },
+      "minimax-voice-id": {
+        "description": "Single voice",
+        "hint": "Single voice ID; see the official documentation."
+      },
+      "minimax-voice-emotion": {
+        "description": "Emotion",
+        "hint": "Controls emotion of synthesized speech. When set to auto, it selects emotion based on text."
+      },
+      "minimax-voice-latex": {
+        "description": "Read LaTeX formulas",
+        "hint": "Read LaTeX formulas, but ensure input text is formatted per the official requirements."
+      },
+      "minimax-voice-english-normalization": {
+        "description": "English text normalization",
+        "hint": "Improves number-reading performance but slightly increases latency."
+      },
+      "rag_options": {
+        "description": "RAG options",
+        "hint": "Knowledge base retrieval settings, optional. Only supported for Agent app types (agent apps, including RAG apps). For Bailian apps, enabling this disables multi-turn conversations.",
+        "pipeline_ids": {
+          "description": "Knowledge base ID list",
+          "hint": "Retrieve all documents in the specified knowledge bases. Go to https://bailian.console.aliyun.com/ Data Apps -> Knowledge Index to create and get IDs."
+        },
+        "file_ids": {
+          "description": "Unstructured document IDs",
+          "hint": "Retrieve specified unstructured documents. Go to https://bailian.console.aliyun.com/ Data Management to create and get IDs."
+        },
+        "output_reference": {
+          "description": "Output knowledge base/document references",
+          "hint": "Append reference sources to the end of each answer. Default is False."
+        }
+      },
+      "sensevoice_hint": {
+        "description": "Deploy SenseVoice",
+        "hint": "Before enabling, install funasr, funasr_onnx, torchaudio, torch, modelscope, and jieba (CPU by default, about 1 GB download), and install ffmpeg. Otherwise STT will not work."
+      },
+      "is_emotion": {
+        "description": "Emotion recognition",
+        "hint": "Enable emotion recognition. happy?sad?angry?neutral?fearful?disgusted?surprised?unknown"
+      },
+      "stt_model": {
+        "description": "Model name",
+        "hint": "Model name on modelscope. Default: iic/SenseVoiceSmall."
+      },
+      "variables": {
+        "description": "Workflow fixed input variables",
+        "hint": "Optional. Fixed workflow input variables are used as workflow inputs. You can also set variables dynamically with /set during a chat. If names conflict, dynamic settings take precedence."
+      },
+      "dashscope_app_type": {
+        "description": "App type",
+        "hint": "Bailian app type."
+      },
+      "timeout": {
+        "description": "Timeout",
+        "hint": "Timeout in seconds."
+      },
+      "openai-tts-voice": {
+        "description": "voice",
+        "hint": "OpenAI TTS voice. OpenAI defaults: 'alloy', 'echo', 'fable', 'onyx', 'nova', 'shimmer'."
+      },
+      "fishaudio-tts-character": {
+        "description": "character",
+        "hint": "Fishaudio TTS character. Default is Klee. More roles: https://fish.audio/zh-CN/discovery"
+      },
+      "fishaudio-tts-reference-id": {
+        "description": "reference_id",
+        "hint": "Fishaudio TTS reference model ID (optional). If set, the model ID is used directly instead of looking up by role name. Example: 626bb6d3f3364c9cbc3aa6a67300a664. More models: https://fish.audio/zh-CN/discovery; open a model detail page to copy the model ID."
+      },
+      "whisper_hint": {
+        "description": "Notes for local Whisper deployment",
+        "hint": "Before enabling, install the openai-whisper library (NVIDIA users download ~2GB mainly for torch and cuda; CPU users download ~1GB), and install ffmpeg. Otherwise STT will not work."
+      },
+      "id": {
+        "description": "ID"
+      },
+      "type": {
+        "description": "Provider category"
+      },
+      "provider_type": {
+        "description": "Provider capability type"
+      },
+      "enable": {
+        "description": "Enable"
+      },
+      "key": {
+        "description": "API Key"
+      },
+      "api_base": {
+        "description": "API Base URL"
+      },
+      "model": {
+        "description": "Model ID",
+        "hint": "Model name, e.g., gpt-4o-mini, deepseek-chat."
+      },
+      "max_context_tokens": {
+        "description": "Model context window size",
+        "hint": "Maximum context tokens. If 0, it auto-fills from model metadata (if available); you can also edit manually."
+      },
+      "dify_api_key": {
+        "description": "API Key",
+        "hint": "Dify API Key. This field is required."
+      },
+      "dify_api_base": {
+        "description": "API Base URL",
+        "hint": "Dify API Base URL. Default: https://api.dify.ai/v1"
+      },
+      "dify_api_type": {
+        "description": "Dify app type",
+        "hint": "Dify API type. According to Dify docs, supported types are chat, chatflow, agent, workflow."
+      },
+      "dify_workflow_output_key": {
+        "description": "Dify workflow output variable name",
+        "hint": "Dify workflow output variable name. Only used when app type is workflow. Default: astrbot_wf_output."
+      },
+      "dify_query_input_key": {
+        "description": "Prompt input variable name",
+        "hint": "Input variable name for the message text. Default: astrbot_text_query."
+      },
+      "coze_api_key": {
+        "description": "Coze API Key",
+        "hint": "Coze API key for accessing Coze services."
+      },
+      "bot_id": {
+        "description": "Bot ID",
+        "hint": "Coze bot ID, obtained after creating a bot on the Coze platform."
+      },
+      "coze_api_base": {
+        "description": "API Base URL",
+        "hint": "Base URL for the Coze API. Default: https://api.coze.cn"
+      },
+      "auto_save_history": {
+        "description": "Conversation history managed by Coze",
+        "hint": "When enabled, Coze manages conversation history. AstrBot's locally saved context will not take effect (read-only), and operations on AstrBot context will not apply. If disabled, AstrBot manages the context."
+      }
+    }
+  },
   "help": {
     "documentation": "Official Documentation",
     "support": "Join Support Group",
diff --git a/dashboard/src/i18n/locales/en-US/features/platform.json b/dashboard/src/i18n/locales/en-US/features/platform.json
index ea1bc01808..64448ca1ea 100644
--- a/dashboard/src/i18n/locales/en-US/features/platform.json
+++ b/dashboard/src/i18n/locales/en-US/features/platform.json
@@ -45,12 +45,67 @@
     },
     "invalidPlatformId": "Platform ID cannot contain ':' or '!'."
   },
+  "createDialog": {
+    "step1Title": "Choose Platform Category",
+    "step1Hint": "Where do you want to connect the bot? e.g. QQ, WeCom, Feishu, Discord, Telegram.",
+    "platformTypeLabel": "Platform Category",
+    "configFileTitle": "Config File",
+    "optional": "Optional",
+    "configHint": "How do you want to configure the bot? The config file includes model, persona, knowledge base, plugins, and more.",
+    "configDefaultHint": "Uses the default config file \"default\" by default. You can configure it later.",
+    "useExistingConfig": "Use existing config file",
+    "selectConfigLabel": "Select config file",
+    "createNewConfig": "Create new config file",
+    "newConfigNameLabel": "New config name",
+    "newConfigTitle": "Use new config file",
+    "newConfigLoadFailed": "Failed to load default config template",
+    "addRouteRule": "Add route rule",
+    "viewMode": "View",
+    "editMode": "Edit",
+    "noRouteRules": "No route rules for this platform. The default config file will be used.",
+    "sessionIdPlaceholder": "Session ID or *",
+    "allSessions": "All sessions",
+    "configMissing": "Config file not found",
+    "routeHint": "When delivering messages, the first matching config file from top to bottom is used based on session source. Use * to match all. Use /sid to get the session ID. If none match, the default config file is used.",
+    "warningContinue": "Ignore warning and continue",
+    "warningEditAgain": "Edit again",
+    "configDrawerTitle": "Config File Management",
+    "configDrawerIdLabel": "ID",
+    "configTableHeaders": {
+      "configId": "Config ID linked to this instance",
+      "scope": "Scope in this instance"
+    },
+    "routeTableHeaders": {
+      "source": "Message Source (Type: Session ID)",
+      "config": "Config File",
+      "actions": "Actions"
+    },
+    "messageTypeOptions": {
+      "all": "All messages",
+      "group": "Group messages (GroupMessage)",
+      "friend": "Direct messages (FriendMessage)"
+    },
+    "messageTypeLabels": {
+      "all": "All messages",
+      "group": "Group messages",
+      "friend": "Direct messages"
+    }
+  },
   "messages": {
     "updateSuccess": "Update successful!",
     "addSuccess": "Add successful!",
     "deleteSuccess": "Delete successful!",
     "statusUpdateSuccess": "Status update successful!",
-    "deleteConfirm": "Are you sure you want to delete platform adapter"
+    "deleteConfirm": "Are you sure you want to delete platform adapter",
+    "configNotFoundOpenConfig": "Target config file not found. Opened the config page for review.",
+    "updateMissingPlatformId": "Update failed: missing platform ID.",
+    "platformUpdateFailed": "Platform update failed.",
+    "addSuccessWithConfig": "Platform added. Config file updated.",
+    "configIdMissing": "Unable to get config file ID.",
+    "routingUpdateFailed": "Failed to update routing table: {message}",
+    "createConfigFailed": "Failed to create config file: {message}",
+    "platformIdMissing": "Unable to get platform ID.",
+    "routingSaveFailed": "Failed to save routing table: {message}"
   },
   "status": {
     "enabled": "Enabled",
diff --git a/dashboard/src/i18n/locales/en-US/features/provider.json b/dashboard/src/i18n/locales/en-US/features/provider.json
index 8d80d0b0b8..505e5b729a 100644
--- a/dashboard/src/i18n/locales/en-US/features/provider.json
+++ b/dashboard/src/i18n/locales/en-US/features/provider.json
@@ -91,6 +91,7 @@
   },
   "providerSources": {
     "title": "Provider Sources",
+    "add": "Add",
     "empty": "No provider sources",
     "selectHint": "Please select a provider source",
     "save": "Save Configuration",
@@ -141,4 +142,4 @@
       "modelId": "Model ID"
     }
   }
-} 
\ No newline at end of file
+} 
diff --git a/dashboard/src/i18n/locales/zh-CN/features/config-metadata.json b/dashboard/src/i18n/locales/zh-CN/features/config-metadata.json
index 6620f1cb30..300883d5cc 100644
--- a/dashboard/src/i18n/locales/zh-CN/features/config-metadata.json
+++ b/dashboard/src/i18n/locales/zh-CN/features/config-metadata.json
@@ -193,7 +193,10 @@
         },
         "context_limit_reached_strategy": {
           "description": "超出模型上下文窗口时的处理方式",
-          "labels": ["按对话轮数截断", "由 LLM 压缩上下文"],
+          "labels": [
+            "按对话轮数截断",
+            "由 LLM 压缩上下文"
+          ],
           "hint": "当按对话轮数截断时，会根据上面\"丢弃对话轮数\"的配置丢弃最旧的 N 轮对话。当由 LLM 压缩上下文时，会使用指定的模型进行上下文压缩。"
         },
         "llm_compress_instruction": {
@@ -268,7 +271,6 @@
             "关闭流式回复"
           ]
         },
-
         "wake_prefix": {
           "description": "LLM 聊天额外唤醒前缀",
           "hint": "如果唤醒前缀为 /, 额外聊天唤醒前缀为 chat,则需要 /chat 才会触发 LLM 请求"
@@ -291,6 +293,235 @@
   },
   "platform_group": {
     "name": "平台配置",
+    "platform": {
+      "description": "消息平台适配器",
+      "active_send_mode": {
+        "description": "是否换用主动发送接口"
+      },
+      "appid": {
+        "description": "appid",
+        "hint": "必填项。QQ 官方机器人平台的 appid。如何获取请参考文档。"
+      },
+      "callback_server_host": {
+        "description": "回调服务器主机",
+        "hint": "回调服务器主机。留空则不启用回调服务器。"
+      },
+      "card_template_id": {
+        "description": "卡片模板 ID",
+        "hint": "可选。钉钉互动卡片模板 ID。启用后将使用互动卡片进行流式回复。"
+      },
+      "discord_activity_name": {
+        "description": "Discord 活动名称",
+        "hint": "可选的 Discord 活动名称。留空则不设置活动。"
+      },
+      "discord_command_register": {
+        "description": "是否自动将插件指令注册为 Discord 斜杠指令"
+      },
+      "discord_proxy": {
+        "description": "Discord 代理地址",
+        "hint": "可选的代理地址：http://ip:port"
+      },
+      "discord_token": {
+        "description": "Discord Bot Token",
+        "hint": "在此处填入你的 Discord Bot Token"
+      },
+      "enable": {
+        "description": "启用",
+        "hint": "是否启用该适配器。未启用的适配器对应的消息平台将不会接收到消息。"
+      },
+      "enable_group_c2c": {
+        "description": "启用消息列表单聊",
+        "hint": "启用后，机器人可以接收到 QQ 消息列表中的私聊消息。你可能需要在 QQ 机器人平台上通过扫描二维码的方式添加机器人为你的好友。详见文档。"
+      },
+      "enable_guild_direct_message": {
+        "description": "启用频道私聊",
+        "hint": "启用后，机器人可以接收到频道的私聊消息。"
+      },
+      "id": {
+        "description": "机器人名称",
+        "hint": "机器人名称"
+      },
+      "is_sandbox": {
+        "description": "沙箱模式"
+      },
+      "kf_name": {
+        "description": "微信客服账号名",
+        "hint": "可选。微信客服账号名(不是 ID)。可在 https://kf.weixin.qq.com/kf/frame#/accounts 获取"
+      },
+      "lark_bot_name": {
+        "description": "飞书机器人的名字",
+        "hint": "请务必填写正确，否则 @ 机器人将无法唤醒，只能通过前缀唤醒。"
+      },
+      "lark_connection_mode": {
+        "description": "订阅方式",
+        "labels": [
+          "长连接模式",
+          "推送至服务器模式"
+        ]
+      },
+      "lark_encrypt_key": {
+        "description": "Encrypt Key",
+        "hint": "用于解密飞书回调数据的加密密钥"
+      },
+      "lark_verification_token": {
+        "description": "Verification Token",
+        "hint": "用于验证飞书回调请求的令牌"
+      },
+      "misskey_allow_insecure_downloads": {
+        "description": "允许不安全下载（禁用 SSL 验证）",
+        "hint": "当远端服务器存在证书问题导致无法正常下载时，自动禁用 SSL 验证作为回退方案。适用于某些图床的证书配置问题。启用有安全风险，仅在必要时使用。"
+      },
+      "misskey_default_visibility": {
+        "description": "默认帖子可见性",
+        "hint": "机器人发帖时的默认可见性设置。public：公开，home：主页时间线，followers：仅关注者。"
+      },
+      "misskey_download_chunk_size": {
+        "description": "流式下载分块大小（字节）",
+        "hint": "流式下载和计算 MD5 时使用的每次读取字节数，过小会增加开销，过大会占用内存。"
+      },
+      "misskey_download_timeout": {
+        "description": "远端下载超时时间（秒）",
+        "hint": "下载远程文件时的超时时间（秒），用于异步上传回退到本地上传的场景。"
+      },
+      "misskey_enable_chat": {
+        "description": "启用聊天消息响应",
+        "hint": "启用后，机器人将会监听和响应私信聊天消息"
+      },
+      "misskey_enable_file_upload": {
+        "description": "启用文件上传到 Misskey",
+        "hint": "启用后，适配器会尝试将消息链中的文件上传到 Misskey。URL 文件会先尝试服务器端上传，异步上传失败时会回退到下载后本地上传。"
+      },
+      "misskey_instance_url": {
+        "description": "Misskey 实例 URL",
+        "hint": "例如 https://misskey.example，填写 Bot 账号所在的 Misskey 实例地址"
+      },
+      "misskey_local_only": {
+        "description": "仅限本站（不参与联合）",
+        "hint": "启用后，机器人发出的帖子将仅在本实例可见，不会联合到其他实例"
+      },
+      "misskey_max_download_bytes": {
+        "description": "最大允许下载字节数（超出则中止）",
+        "hint": "如果希望限制下载文件的最大大小以防止 OOM，请填写最大字节数；留空或 null 表示不限制。"
+      },
+      "misskey_token": {
+        "description": "Misskey Access Token",
+        "hint": "连接服务设置生成的 API 鉴权访问令牌（Access token）"
+      },
+      "misskey_upload_concurrency": {
+        "description": "并发上传限制",
+        "hint": "同时进行的文件上传任务上限（整数，默认 3）。"
+      },
+      "misskey_upload_folder": {
+        "description": "上传到网盘的目标文件夹 ID",
+        "hint": "可选：填写 Misskey 网盘中目标文件夹的 ID，上传的文件将放置到该文件夹内。留空则使用账号网盘根目录。"
+      },
+      "port": {
+        "description": "回调服务器端口",
+        "hint": "回调服务器端口。留空则不启用回调服务器。"
+      },
+      "satori_api_base_url": {
+        "description": "Satori API 终结点",
+        "hint": "Satori API 的基础地址。"
+      },
+      "satori_auto_reconnect": {
+        "description": "启用自动重连",
+        "hint": "断开连接时是否自动重新连接 WebSocket。"
+      },
+      "satori_endpoint": {
+        "description": "Satori WebSocket 终结点",
+        "hint": "Satori 事件的 WebSocket 端点。"
+      },
+      "satori_heartbeat_interval": {
+        "description": "Satori 心跳间隔",
+        "hint": "发送心跳消息的间隔（秒）。"
+      },
+      "satori_reconnect_delay": {
+        "description": "Satori 重连延迟",
+        "hint": "尝试重新连接前的延迟时间（秒）。"
+      },
+      "satori_token": {
+        "description": "Satori 令牌",
+        "hint": "用于 Satori API 身份验证的令牌。"
+      },
+      "secret": {
+        "description": "secret",
+        "hint": "必填项。"
+      },
+      "slack_connection_mode": {
+        "description": "Slack Connection Mode",
+        "hint": "The connection mode for Slack. `webhook` uses a webhook server, `socket` uses Slack's Socket Mode."
+      },
+      "slack_webhook_host": {
+        "description": "Slack Webhook Host",
+        "hint": "Only valid when Slack connection mode is `webhook`."
+      },
+      "slack_webhook_path": {
+        "description": "Slack Webhook Path",
+        "hint": "Only valid when Slack connection mode is `webhook`."
+      },
+      "slack_webhook_port": {
+        "description": "Slack Webhook Port",
+        "hint": "Only valid when Slack connection mode is `webhook`."
+      },
+      "telegram_command_auto_refresh": {
+        "description": "Telegram 命令自动刷新",
+        "hint": "启用后，AstrBot 将会在运行时自动刷新 Telegram 命令。(单独设置此项无效)"
+      },
+      "telegram_command_register": {
+        "description": "Telegram 命令注册",
+        "hint": "启用后，AstrBot 将会自动注册 Telegram 命令。"
+      },
+      "telegram_command_register_interval": {
+        "description": "Telegram 命令自动刷新间隔",
+        "hint": "Telegram 命令自动刷新间隔，单位为秒。"
+      },
+      "telegram_token": {
+        "description": "Bot Token",
+        "hint": "如果你的网络环境为中国大陆，请在 `其他配置` 处设置代理或更改 api_base。"
+      },
+      "type": {
+        "description": "适配器类型"
+      },
+      "unified_webhook_mode": {
+        "description": "统一 Webhook 模式",
+        "hint": "启用后，将使用 AstrBot 统一 Webhook 入口，无需单独开启端口。回调地址为 /api/platform/webhook/{webhook_uuid}。"
+      },
+      "webhook_uuid": {
+        "description": "Webhook UUID",
+        "hint": "统一 Webhook 模式下的唯一标识符，创建平台时自动生成。"
+      },
+      "wecom_ai_bot_name": {
+        "description": "企业微信智能机器人的名字",
+        "hint": "请务必填写正确，否则无法使用一些指令。"
+      },
+      "wecomaibot_friend_message_welcome_text": {
+        "description": "企业微信智能机器人私聊欢迎语",
+        "hint": "当用户当天进入智能机器人单聊会话，回复欢迎语，留空则不回复。"
+      },
+      "wecomaibot_init_respond_text": {
+        "description": "企业微信智能机器人初始响应文本",
+        "hint": "当机器人收到消息时，首先回复的文本内容。留空则使用默认值。"
+      },
+      "wpp_active_message_poll": {
+        "description": "是否启用主动消息轮询",
+        "hint": "只有当你发现微信消息没有按时同步到 AstrBot 时，才需要启用这个功能，默认不启用。"
+      },
+      "wpp_active_message_poll_interval": {
+        "description": "主动消息轮询间隔",
+        "hint": "主动消息轮询间隔，单位为秒，默认 3 秒，最大不要超过 60 秒，否则可能被认为是旧消息。"
+      },
+      "ws_reverse_host": {
+        "description": "反向 Websocket 主机",
+        "hint": "AstrBot 将作为服务器端。"
+      },
+      "ws_reverse_port": {
+        "description": "反向 Websocket 端口"
+      },
+      "ws_reverse_token": {
+        "description": "反向 Websocket Token",
+        "hint": "反向 Websocket Token。未设置则不启用 Token 验证。"
+      }
+    },
     "general": {
       "description": "基本",
       "admins_id": {
@@ -616,6 +847,443 @@
       }
     }
   },
+  "provider_group": {
+    "provider": {
+      "genie_onnx_model_dir": {
+        "description": "ONNX Model Directory",
+        "hint": "The directory path containing the ONNX model files"
+      },
+      "genie_language": {
+        "description": "Language"
+      },
+      "xai_native_search": {
+        "description": "启用原生搜索功能",
+        "hint": "启用后，将通过 xAI 的 Chat Completions 原生 Live Search 进行联网检索（按需计费）。仅对 xAI 提供商生效。"
+      },
+      "rerank_api_base": {
+        "description": "重排序模型 API Base URL",
+        "hint": "AstrBot 会在请求时在末尾加上 /v1/rerank。"
+      },
+      "rerank_api_key": {
+        "description": "API Key",
+        "hint": "如果不需要 API Key, 请留空。"
+      },
+      "rerank_model": {
+        "description": "重排序模型名称"
+      },
+      "return_documents": {
+        "description": "是否在排序结果中返回文档原文",
+        "hint": "默认值false，以减少网络传输开销。"
+      },
+      "instruct": {
+        "description": "自定义排序任务类型说明",
+        "hint": "仅在使用 qwen3-rerank 模型时生效。建议使用英文撰写。"
+      },
+      "launch_model_if_not_running": {
+        "description": "模型未运行时自动启动",
+        "hint": "如果模型当前未在 Xinference 服务中运行，是否尝试自动启动它。在生产环境中建议关闭。"
+      },
+      "modalities": {
+        "description": "模型能力",
+        "hint": "模型支持的模态。如所填写的模型不支持图像，请取消勾选图像。",
+        "labels": [
+          "文本",
+          "图像",
+          "工具使用"
+        ]
+      },
+      "custom_headers": {
+        "description": "自定义添加请求头",
+        "hint": "此处添加的键值对将被合并到 OpenAI SDK 的 default_headers 中，用于自定义 HTTP 请求头。值必须为字符串。"
+      },
+      "custom_extra_body": {
+        "description": "自定义请求体参数",
+        "hint": "用于在请求时添加额外的参数，如 temperature、top_p、max_tokens 等。",
+        "template_schema": {
+          "temperature": {
+            "description": "温度参数",
+            "hint": "控制输出的随机性，范围通常为 0-2。值越高越随机。",
+            "name": "Temperature"
+          },
+          "top_p": {
+            "description": "Top-p 采样",
+            "hint": "核采样参数，范围通常为 0-1。控制模型考虑的概率质量。",
+            "name": "Top-p"
+          },
+          "max_tokens": {
+            "description": "最大令牌数",
+            "hint": "生成的最大令牌数。",
+            "name": "Max Tokens"
+          }
+        }
+      },
+      "gpt_weights_path": {
+        "description": "GPT模型文件路径",
+        "hint": "即“.ckpt”后缀的文件，请使用绝对路径，路径两端不要带双引号，不填则默认用GPT_SoVITS内置的SoVITS模型(建议直接在GPT_SoVITS中改默认模型)"
+      },
+      "sovits_weights_path": {
+        "description": "SoVITS模型文件路径",
+        "hint": "即“.pth”后缀的文件，请使用绝对路径，路径两端不要带双引号，不填则默认用GPT_SoVITS内置的SoVITS模型(建议直接在GPT_SoVITS中改默认模型)"
+      },
+      "gsv_default_parms": {
+        "description": "GPT_SoVITS默认参数",
+        "hint": "参考音频文件路径、参考音频文本必填，其他参数根据个人爱好自行填写",
+        "gsv_ref_audio_path": {
+          "description": "参考音频文件路径",
+          "hint": "必填！请使用绝对路径！路径两端不要带双引号！"
+        },
+        "gsv_prompt_text": {
+          "description": "参考音频文本",
+          "hint": "必填！请填写参考音频讲述的文本"
+        },
+        "gsv_prompt_lang": {
+          "description": "参考音频文本语言",
+          "hint": "请填写参考音频讲述的文本的语言，默认为中文"
+        },
+        "gsv_aux_ref_audio_paths": {
+          "description": "辅助参考音频文件路径",
+          "hint": "辅助参考音频文件，可不填"
+        },
+        "gsv_text_lang": {
+          "description": "文本语言",
+          "hint": "默认为中文"
+        },
+        "gsv_top_k": {
+          "description": "生成语音的多样性",
+          "hint": ""
+        },
+        "gsv_top_p": {
+          "description": "核采样的阈值",
+          "hint": ""
+        },
+        "gsv_temperature": {
+          "description": "生成语音的随机性",
+          "hint": ""
+        },
+        "gsv_text_split_method": {
+          "description": "切分文本的方法",
+          "hint": "可选值：  `cut0`：不切分    `cut1`：四句一切   `cut2`：50字一切    `cut3`：按中文句号切    `cut4`：按英文句号切    `cut5`：按标点符号切"
+        },
+        "gsv_batch_size": {
+          "description": "批处理大小",
+          "hint": ""
+        },
+        "gsv_batch_threshold": {
+          "description": "批处理阈值",
+          "hint": ""
+        },
+        "gsv_split_bucket": {
+          "description": "将文本分割成桶以便并行处理",
+          "hint": ""
+        },
+        "gsv_speed_factor": {
+          "description": "语音播放速度",
+          "hint": "1为原始语速"
+        },
+        "gsv_fragment_interval": {
+          "description": "语音片段之间的间隔时间",
+          "hint": ""
+        },
+        "gsv_streaming_mode": {
+          "description": "启用流模式",
+          "hint": ""
+        },
+        "gsv_seed": {
+          "description": "随机种子",
+          "hint": "用于结果的可重复性"
+        },
+        "gsv_parallel_infer": {
+          "description": "并行执行推理",
+          "hint": ""
+        },
+        "gsv_repetition_penalty": {
+          "description": "重复惩罚因子",
+          "hint": ""
+        },
+        "gsv_media_type": {
+          "description": "输出媒体的类型",
+          "hint": "建议用wav"
+        }
+      },
+      "embedding_dimensions": {
+        "description": "嵌入维度",
+        "hint": "嵌入向量的维度。根据模型不同，可能需要调整，请参考具体模型的文档。此配置项请务必填写正确，否则将导致向量数据库无法正常工作。"
+      },
+      "embedding_model": {
+        "description": "嵌入模型",
+        "hint": "嵌入模型名称。"
+      },
+      "embedding_api_key": {
+        "description": "API Key"
+      },
+      "embedding_api_base": {
+        "description": "API Base URL"
+      },
+      "volcengine_cluster": {
+        "description": "火山引擎集群",
+        "hint": "若使用语音复刻大模型，可选volcano_icl或volcano_icl_concurr，默认使用volcano_tts"
+      },
+      "volcengine_voice_type": {
+        "description": "火山引擎音色",
+        "hint": "输入声音id(Voice_type)"
+      },
+      "volcengine_speed_ratio": {
+        "description": "语速设置",
+        "hint": "语速设置，范围为 0.2 到 3.0,默认值为 1.0"
+      },
+      "volcengine_volume_ratio": {
+        "description": "音量设置",
+        "hint": "音量设置，范围为 0.0 到 2.0,默认值为 1.0"
+      },
+      "azure_tts_voice": {
+        "description": "音色设置",
+        "hint": "API 音色"
+      },
+      "azure_tts_style": {
+        "description": "风格设置",
+        "hint": "声音特定的讲话风格。 可以表达快乐、同情和平静等情绪。"
+      },
+      "azure_tts_role": {
+        "description": "模仿设置（可选）",
+        "hint": "讲话角色扮演。 声音可以模仿不同的年龄和性别，但声音名称不会更改。 例如，男性语音可以提高音调和改变语调来模拟女性语音，但语音名称不会更改。 如果角色缺失或不受声音的支持，则会忽略此属性。"
+      },
+      "azure_tts_rate": {
+        "description": "语速设置",
+        "hint": "指示文本的讲出速率。可在字词或句子层面应用语速。 速率变化应为原始音频的 0.5 到 2 倍。"
+      },
+      "azure_tts_volume": {
+        "description": "语音音量设置",
+        "hint": "指示语音的音量级别。 可在句子层面应用音量的变化。以从 0.0 到 100.0（从最安静到最大声，例如 75）的数字表示。 默认值为 100.0。"
+      },
+      "azure_tts_region": {
+        "description": "API 地区",
+        "hint": "Azure_TTS 处理数据所在区域，具体参考 https://learn.microsoft.com/zh-cn/azure/ai-services/speech-service/regions"
+      },
+      "azure_tts_subscription_key": {
+        "description": "服务订阅密钥",
+        "hint": "Azure_TTS 服务的订阅密钥（注意不是令牌）"
+      },
+      "dashscope_tts_voice": {
+        "description": "音色"
+      },
+      "gm_resp_image_modal": {
+        "description": "启用图片模态",
+        "hint": "启用后，将支持返回图片内容。需要模型支持，否则会报错。具体支持模型请查看 Google Gemini 官方网站。温馨提示，如果您需要生成图片，请关闭 `启用群员识别` 配置获得更好的效果。"
+      },
+      "gm_native_search": {
+        "description": "启用原生搜索功能",
+        "hint": "启用后所有函数工具将全部失效，免费次数限制请查阅官方文档"
+      },
+      "gm_native_coderunner": {
+        "description": "启用原生代码执行器",
+        "hint": "启用后所有函数工具将全部失效"
+      },
+      "gm_url_context": {
+        "description": "启用URL上下文功能",
+        "hint": "启用后所有函数工具将全部失效"
+      },
+      "gm_safety_settings": {
+        "description": "安全过滤器",
+        "hint": "设置模型输入的内容安全过滤级别。过滤级别分类为NONE(不屏蔽)、HIGH(高风险时屏蔽)、MEDIUM_AND_ABOVE(中等风险及以上屏蔽)、LOW_AND_ABOVE(低风险及以上时屏蔽)，具体参见Gemini API文档。",
+        "harassment": {
+          "description": "骚扰内容",
+          "hint": "负面或有害评论"
+        },
+        "hate_speech": {
+          "description": "仇恨言论",
+          "hint": "粗鲁、无礼或亵渎性质内容"
+        },
+        "sexually_explicit": {
+          "description": "露骨色情内容",
+          "hint": "包含性行为或其他淫秽内容的引用"
+        },
+        "dangerous_content": {
+          "description": "危险内容",
+          "hint": "宣扬、助长或鼓励有害行为的信息"
+        }
+      },
+      "gm_thinking_config": {
+        "description": "思考配置",
+        "budget": {
+          "description": "思考预算",
+          "hint": "用于指定模型推理时使用的思考 token 数量上限。参见: https://ai.google.dev/gemini-api/docs/thinking#set-budget"
+        },
+        "level": {
+          "description": "思考级别",
+          "hint": "推荐用于 Gemini 3 及以上模型，可控制推理行为。参见: https://ai.google.dev/gemini-api/docs/thinking#thinking-levels"
+        }
+      },
+      "anth_thinking_config": {
+        "description": "思考配置",
+        "budget": {
+          "description": "思考预算",
+          "hint": "Anthropic thinking.budget_tokens 参数。必须 >= 1024。参见: https://platform.claude.com/docs/en/build-with-claude/extended-thinking"
+        }
+      },
+      "minimax-group-id": {
+        "description": "用户组",
+        "hint": "于账户管理->基本信息中可见"
+      },
+      "minimax-langboost": {
+        "description": "指定语言/方言",
+        "hint": "增强对指定的小语种和方言的识别能力，设置后可以提升在指定小语种/方言场景下的语音表现"
+      },
+      "minimax-voice-speed": {
+        "description": "语速",
+        "hint": "生成声音的语速, 取值[0.5, 2], 默认为1.0, 取值越大，语速越快"
+      },
+      "minimax-voice-vol": {
+        "description": "音量",
+        "hint": "生成声音的音量, 取值(0, 10], 默认为1.0, 取值越大，音量越高"
+      },
+      "minimax-voice-pitch": {
+        "description": "语调",
+        "hint": "生成声音的语调, 取值[-12, 12], 默认为0"
+      },
+      "minimax-is-timber-weight": {
+        "description": "启用混合音色",
+        "hint": "启用混合音色, 支持以自定义权重混合最多四种音色, 启用后自动忽略单一音色设置"
+      },
+      "minimax-timber-weight": {
+        "description": "混合音色",
+        "hint": "混合音色及其权重, 最多支持四种音色, 权重为整数, 取值[1, 100]. 可在官网API语音调试台预览代码获得预设以及编写模板, 需要严格按照json字符串格式编写, 可以查看控制台判断是否解析成功. 具体结构可参照默认值以及官网代码预览."
+      },
+      "minimax-voice-id": {
+        "description": "单一音色",
+        "hint": "单一音色编号, 详见官网文档"
+      },
+      "minimax-voice-emotion": {
+        "description": "情绪",
+        "hint": "控制合成语音的情绪。当为 auto 时，将根据文本内容自动选择情绪。"
+      },
+      "minimax-voice-latex": {
+        "description": "支持朗读latex公式",
+        "hint": "朗读latex公式, 但是需要确保输入文本按官网要求格式化"
+      },
+      "minimax-voice-english-normalization": {
+        "description": "支持英语文本规范化",
+        "hint": "可提升数字阅读场景的性能，但会略微增加延迟"
+      },
+      "rag_options": {
+        "description": "RAG 选项",
+        "hint": "检索知识库设置, 非必填。仅 Agent 应用类型支持(智能体应用, 包括 RAG 应用)。阿里云百炼应用开启此功能后将无法多轮对话。",
+        "pipeline_ids": {
+          "description": "知识库 ID 列表",
+          "hint": "对指定知识库内所有文档进行检索, 前往 https://bailian.console.aliyun.com/ 数据应用->知识索引创建和获取 ID。"
+        },
+        "file_ids": {
+          "description": "非结构化文档 ID, 传入该参数将对指定非结构化文档进行检索。",
+          "hint": "对指定非结构化文档进行检索。前往 https://bailian.console.aliyun.com/ 数据管理创建和获取 ID。"
+        },
+        "output_reference": {
+          "description": "是否输出知识库/文档的引用",
+          "hint": "在每次回答尾部加上引用源。默认为 False。"
+        }
+      },
+      "sensevoice_hint": {
+        "description": "部署SenseVoice",
+        "hint": "启用前请 pip 安装 funasr、funasr_onnx、torchaudio、torch、modelscope、jieba 库（默认使用CPU，大约下载 1 GB），并且安装 ffmpeg。否则将无法正常转文字。"
+      },
+      "is_emotion": {
+        "description": "情绪识别",
+        "hint": "是否开启情绪识别。happy｜sad｜angry｜neutral｜fearful｜disgusted｜surprised｜unknown"
+      },
+      "stt_model": {
+        "description": "模型名称",
+        "hint": "modelscope 上的模型名称。默认：iic/SenseVoiceSmall。"
+      },
+      "variables": {
+        "description": "工作流固定输入变量",
+        "hint": "可选。工作流固定输入变量，将会作为工作流的输入。也可以在对话时使用 /set 指令动态设置变量。如果变量名冲突，优先使用动态设置的变量。"
+      },
+      "dashscope_app_type": {
+        "description": "应用类型",
+        "hint": "百炼应用的应用类型。"
+      },
+      "timeout": {
+        "description": "超时时间",
+        "hint": "超时时间，单位为秒。"
+      },
+      "openai-tts-voice": {
+        "description": "voice",
+        "hint": "OpenAI TTS 的声音。OpenAI 默认支持：'alloy', 'echo', 'fable', 'onyx', 'nova', 'shimmer'"
+      },
+      "fishaudio-tts-character": {
+        "description": "character",
+        "hint": "fishaudio TTS 的角色。默认为可莉。更多角色请访问：https://fish.audio/zh-CN/discovery"
+      },
+      "fishaudio-tts-reference-id": {
+        "description": "reference_id",
+        "hint": "fishaudio TTS 的参考模型ID（可选）。如果填入此字段，将直接使用模型ID而不通过角色名称查询。例如：626bb6d3f3364c9cbc3aa6a67300a664。更多模型请访问：https://fish.audio/zh-CN/discovery，进入模型详情界面后可复制模型ID"
+      },
+      "whisper_hint": {
+        "description": "本地部署 Whisper 模型须知",
+        "hint": "启用前请 pip 安装 openai-whisper 库（N卡用户大约下载 2GB，主要是 torch 和 cuda，CPU 用户大约下载 1 GB），并且安装 ffmpeg。否则将无法正常转文字。"
+      },
+      "id": {
+        "description": "ID"
+      },
+      "type": {
+        "description": "模型提供商种类"
+      },
+      "provider_type": {
+        "description": "模型提供商能力种类"
+      },
+      "enable": {
+        "description": "启用"
+      },
+      "key": {
+        "description": "API Key"
+      },
+      "api_base": {
+        "description": "API Base URL"
+      },
+      "model": {
+        "description": "模型 ID",
+        "hint": "模型名称，如 gpt-4o-mini, deepseek-chat。"
+      },
+      "max_context_tokens": {
+        "description": "模型上下文窗口大小",
+        "hint": "模型最大上下文 Token 大小。如果为 0，则会自动从模型元数据填充（如有），也可手动修改。"
+      },
+      "dify_api_key": {
+        "description": "API Key",
+        "hint": "Dify API Key。此项必填。"
+      },
+      "dify_api_base": {
+        "description": "API Base URL",
+        "hint": "Dify API Base URL。默认为 https://api.dify.ai/v1"
+      },
+      "dify_api_type": {
+        "description": "Dify 应用类型",
+        "hint": "Dify API 类型。根据 Dify 官网，目前支持 chat, chatflow, agent, workflow 三种应用类型。"
+      },
+      "dify_workflow_output_key": {
+        "description": "Dify Workflow 输出变量名",
+        "hint": "Dify Workflow 输出变量名。当应用类型为 workflow 时才使用。默认为 astrbot_wf_output。"
+      },
+      "dify_query_input_key": {
+        "description": "Prompt 输入变量名",
+        "hint": "发送的消息文本内容对应的输入变量名。默认为 astrbot_text_query。"
+      },
+      "coze_api_key": {
+        "description": "Coze API Key",
+        "hint": "Coze API 密钥，用于访问 Coze 服务。"
+      },
+      "bot_id": {
+        "description": "Bot ID",
+        "hint": "Coze 机器人的 ID，在 Coze 平台上创建机器人后获得。"
+      },
+      "coze_api_base": {
+        "description": "API Base URL",
+        "hint": "Coze API 的基础 URL 地址，默认为 https://api.coze.cn"
+      },
+      "auto_save_history": {
+        "description": "由 Coze 管理对话记录",
+        "hint": "启用后，将由 Coze 进行对话历史记录管理, 此时 AstrBot 本地保存的上下文不会生效(仅供浏览), 对 AstrBot 的上下文进行的操作也不会生效。如果为禁用, 则使用 AstrBot 管理上下文。"
+      }
+    }
+  },
   "help": {
     "documentation": "官方文档",
     "support": "加群询问",
diff --git a/dashboard/src/i18n/locales/zh-CN/features/platform.json b/dashboard/src/i18n/locales/zh-CN/features/platform.json
index 204e5c58bf..f26d9507dd 100644
--- a/dashboard/src/i18n/locales/zh-CN/features/platform.json
+++ b/dashboard/src/i18n/locales/zh-CN/features/platform.json
@@ -45,12 +45,67 @@
     },
     "invalidPlatformId": "平台 ID 不能包含 ':' 或 '!'。"
   },
+  "createDialog": {
+    "step1Title": "选择消息平台类别",
+    "step1Hint": "想把机器人接入到哪里？如 QQ、企业微信、飞书、Discord、Telegram 等。",
+    "platformTypeLabel": "消息平台类别",
+    "configFileTitle": "配置文件",
+    "optional": "可选",
+    "configHint": "想如何配置机器人？配置文件包含了聊天模型、人格、知识库、插件范围等丰富的机器人配置项。",
+    "configDefaultHint": "默认使用默认配置文件 “default”。您也可以稍后配置。",
+    "useExistingConfig": "使用现有配置文件",
+    "selectConfigLabel": "选择配置文件",
+    "createNewConfig": "创建新配置文件",
+    "newConfigNameLabel": "新配置文件名称",
+    "newConfigTitle": "使用新的配置文件",
+    "newConfigLoadFailed": "无法加载默认配置模板",
+    "addRouteRule": "添加路由规则",
+    "viewMode": "查看",
+    "editMode": "编辑",
+    "noRouteRules": "该平台暂无路由规则，将使用默认配置文件",
+    "sessionIdPlaceholder": "会话ID或*",
+    "allSessions": "全部会话",
+    "configMissing": "配置文件不存在",
+    "routeHint": "*消息下发时，根据会话来源按顺序从上到下匹配首个符合条件的配置文件。使用 * 表示匹配所有。使用 /sid 指令获取会话 ID。全部不匹配时将使用默认配置文件。",
+    "warningContinue": "无视警告并继续创建",
+    "warningEditAgain": "重新修改",
+    "configDrawerTitle": "配置文件管理",
+    "configDrawerIdLabel": "ID",
+    "configTableHeaders": {
+      "configId": "与此实例关联的配置文件 ID",
+      "scope": "在此实例下的应用范围"
+    },
+    "routeTableHeaders": {
+      "source": "消息会话来源(消息类型:会话 ID)",
+      "config": "使用配置文件",
+      "actions": "操作"
+    },
+    "messageTypeOptions": {
+      "all": "全部消息",
+      "group": "群组消息(GroupMessage)",
+      "friend": "私聊消息(FriendMessage)"
+    },
+    "messageTypeLabels": {
+      "all": "全部消息",
+      "group": "群组消息",
+      "friend": "私聊消息"
+    }
+  },
   "messages": {
     "updateSuccess": "更新成功!",
     "addSuccess": "添加成功!",
     "deleteSuccess": "删除成功!",
     "statusUpdateSuccess": "状态更新成功!",
-    "deleteConfirm": "确定要删除平台适配器"
+    "deleteConfirm": "确定要删除平台适配器",
+    "configNotFoundOpenConfig": "目标配置文件不存在，已打开配置页面以便检查。",
+    "updateMissingPlatformId": "更新失败，缺少平台 ID。",
+    "platformUpdateFailed": "平台更新失败。",
+    "addSuccessWithConfig": "平台添加成功，配置文件已更新",
+    "configIdMissing": "无法获取配置文件ID。",
+    "routingUpdateFailed": "更新路由表失败: {message}",
+    "createConfigFailed": "创建新配置文件失败: {message}",
+    "platformIdMissing": "无法获取平台 ID。",
+    "routingSaveFailed": "保存路由表失败: {message}"
   },
   "status": {
     "enabled": "已启用",
diff --git a/dashboard/src/i18n/locales/zh-CN/features/provider.json b/dashboard/src/i18n/locales/zh-CN/features/provider.json
index 10d8edc7c0..76cd347db9 100644
--- a/dashboard/src/i18n/locales/zh-CN/features/provider.json
+++ b/dashboard/src/i18n/locales/zh-CN/features/provider.json
@@ -92,6 +92,7 @@
   },
   "providerSources": {
     "title": "提供商源",
+    "add": "新增",
     "empty": "暂无提供商源",
     "selectHint": "请选择一个提供商源",
     "save": "保存配置",
@@ -142,4 +143,4 @@
       "modelId": "模型 ID"
     }
   }
-} 
\ No newline at end of file
+} 
diff --git a/dashboard/src/utils/platformUtils.js b/dashboard/src/utils/platformUtils.js
index cac9a7fd71..47f494193f 100644
--- a/dashboard/src/utils/platformUtils.js
+++ b/dashboard/src/utils/platformUtils.js
@@ -14,6 +14,8 @@ export function getPlatformIcon(name) {
     return new URL('@/assets/images/platform_logos/qq.png', import.meta.url).href
   } else if (name === 'wecom' || name === 'wecom_ai_bot') {
     return new URL('@/assets/images/platform_logos/wecom.png', import.meta.url).href
+  } else if (name === 'weixin_official_account') {
+    return new URL('@/assets/images/platform_logos/wechat.png', import.meta.url).href
   } else if (name === 'lark') {
     return new URL('@/assets/images/platform_logos/lark.png', import.meta.url).href
   } else if (name === 'dingtalk') {