fix(settings): 补齐CUDA运行组件下载与安装入口

frontend/src/features/settings/LocalModelSettings.spec.ts

@@ -0,0 +1,26 @@
+// @vitest-environment happy-dom
+import { mount, flushPromises } from '@vue/test-utils'
+import { expect, it, vi } from 'vitest'
+import { apiClient } from '@/services/apiClient'
+import LocalModelSettings from './LocalModelSettings.vue'
+
+vi.mock('@/services/apiClient', () => ({apiClient:{get:vi.fn(),post:vi.fn()}}))
+it('shows an optional CUDA installer and live installation stage', async () => {
+  vi.mocked(apiClient.get).mockImplementation(async (url) => url.includes('runtime-components')
+    ? {status:'not_installed', stage:'尚未安装', supported:true, cuda_available:null,custom_interpreter:false}
+    : {items:[],config:null,runtime_installed:true,last_inference:null})
+  vi.mocked(apiClient.post).mockResolvedValue({status:'installing',stage:'下载并安装 PyTorch CUDA（约 3 GB）',supported:true})
+  const wrapper = mount(LocalModelSettings)
+  try {
+    await flushPromises()
+    const button = wrapper.findAll('button').find(b => b.text() === '下载并安装 CUDA 组件')!
+    expect(button.exists()).toBe(true)
+    expect(apiClient.post).not.toHaveBeenCalled()
+    await button.trigger('click')
+    await flushPromises()
+    expect(apiClient.post).toHaveBeenCalledWith('/api/local-models/runtime-components/cuda')
+    expect(wrapper.text()).toContain('下载并安装 PyTorch CUDA')
+    expect(wrapper.get('progress').attributes('value')).toBeUndefined()
+    expect(button.attributes('disabled')).toBeDefined()
+  } finally {wrapper.unmount()}
+})

frontend/src/features/settings/LocalModelSettings.vue

@@ -6,6 +6,16 @@ interface Model {key: string; name: string; capability: string; revision: string
 const items = ref<Model[]>([])
 const config = ref<Config | null>(null)
 const installed = ref(false)
+interface CudaComponent {status:string;stage:string;cuda_available:boolean|null;supported:boolean;custom_interpreter:boolean;error?:string;torch?:string}
+const cuda = ref<CudaComponent|null>(null)
+const cudaError = ref('')
+async function loadCuda() {
+  try { cuda.value = await apiClient.get<CudaComponent>('/api/local-models/runtime-components/cuda'); cudaError.value = '' }
+  catch(e) { cudaError.value = (e as Error).message }
+}
+async function installCuda() {
+  await act(async () => { cuda.value = await apiClient.post<CudaComponent>('/api/local-models/runtime-components/cuda') })
+}
 const lastInference = ref<{actual_device:string;requested_device:string;inference_seconds?:number;elapsed_seconds?:number;status?:string;error_code?:string}|null>(null)
 const error = ref('')
 const dirty = ref(false)
@@ -15,6 +25,7 @@ let stopped = false
 const size = (bytes: number | null) => bytes === null ? '未知' : `${(bytes / 1024 / 1024).toFixed(1)} MiB`
 const labels: Record<string,string> = {not_installed:'未下载',downloading:'下载中',installed:'已下载并校验',failed:'下载失败',interrupted:'已中断，可续传'}
 async function load() {
+  await loadCuda()
   try {
     const data = await apiClient.get<{items:Model[];config:Config;runtime_installed:boolean;last_inference:typeof lastInference.value}>('/api/local-models')
     items.value = data.items; installed.value = data.runtime_installed
@@ -45,6 +56,20 @@ onUnmounted(() => { stopped = true; clearTimeout(timer) })
     <p v-if="error" class="error-banner" role="alert">{{ error }}</p>
     <p v-if="lastInference" class="subtle">最近实际运行：{{ lastInference.actual_device || '未开始推理' }} · 请求设备 {{ lastInference.requested_device }} · 推理 {{ (lastInference.inference_seconds ?? lastInference.elapsed_seconds ?? 0).toFixed(2) }} 秒 · {{ lastInference.status }} {{ lastInference.error_code || '' }}</p>
     <p v-if="!installed" class="subtle">尚未安装模型运行环境。在项目根目录执行 <code>./backend/scripts/install-model-runtime.ps1</code>；CUDA 选装追加 <code>-Device cuda</code>。</p>
+    <article class="item-card cuda-components" aria-label="CUDA 运行组件">
+      <h4>CUDA 运行组件（可选）</h4>
+      <p class="subtle">默认使用 CPU。需要 NVIDIA GPU 加速时下载此组件，约 3 GB，安装时还需要额外磁盘空间；不包含显卡驱动和模型权重。</p>
+      <p v-if="cudaError" class="error-text" role="alert">{{ cudaError }} <button class="button-secondary" @click="loadCuda">重新检查</button></p>
+      <template v-if="cuda">
+        <p role="status">{{ cuda.stage }} {{ cuda.torch || '' }}</p>
+        <progress v-if="['checking','installing'].includes(cuda.status)" aria-label="CUDA 组件安装进度" />
+        <p v-if="cuda.error" class="error-text">{{ cuda.error }}</p>
+        <p v-if="!cuda.supported" class="subtle">当前平台暂不支持页面安装，请使用对应平台的模型运行环境。</p>
+        <button v-else-if="cuda.status !== 'installed'" class="button-primary" :disabled="busy || ['checking','installing'].includes(cuda.status)" @click="installCuda">{{ cuda.status === 'installing' ? '正在下载并安装…' : ['failed','interrupted'].includes(cuda.status) ? '重试安装 CUDA 组件' : '下载并安装 CUDA 组件' }}</button>
+        <p v-if="cuda.status === 'installed'" class="subtle">{{ cuda.cuda_available ? '组件已就绪。在下方选择 CUDA 并保存即可启用。' : '组件已安装，但当前未检测到可用 CUDA 设备，将回退 CPU。' }}</p>
+        <p v-if="cuda.custom_interpreter" class="subtle">当前后端设置了 APP_MODEL_PYTHON，优先使用指定环境；要使用页面安装的组件，请移除该覆盖并重启后端。</p>
+      </template>
+    </article>
     <form v-if="config" @submit.prevent="save" @input="dirty = true" @change="dirty = true">
       <div class="runtime-grid"><label>请求设备<select v-model="config.device" class="select"><option value="cpu">CPU（默认）</option><option value="cuda">CUDA（不可用则 CPU）</option></select></label>
       <label>Embedding<select v-model="config.embedding_model" class="select"><option value="bekko">Bekko A8M</option><option value="granite">Granite 97M 多语言</option></select></label>