feat(运维监控): 增强监控功能和健康评分系统

后端改进：
- 新增健康评分计算服务（ops_health_score.go）
- 添加分布式锁支持（ops_advisory_lock.go）
- 优化指标采集和聚合逻辑
- 新增运维指标采集间隔配置（60-3600秒）
- 移除未使用的WebSocket查询token认证中间件
- 改进清理服务和告警评估逻辑

前端改进：
- 简化OpsDashboard组件结构
- 完善国际化文本（中英文）
- 新增运维监控相关API类型定义
- 添加运维指标采集间隔设置界面
- 优化错误详情模态框

测试：
- 添加健康评分单元测试
- 更新API契约测试

frontend/src/api/admin/ops.ts

@@ -46,6 +46,8 @@ export interface OpsDashboardOverview {
   platform: string
   group_id?: number | null
 
+  health_score?: number
+
   system_metrics?: OpsSystemMetricsSnapshot | null
   job_heartbeats?: OpsJobHeartbeat[] | null
 
@@ -228,6 +230,9 @@ export interface OpsSystemMetricsSnapshot {
   db_ok?: boolean | null
   redis_ok?: boolean | null
 
+  redis_conn_total?: number | null
+  redis_conn_idle?: number | null
+
   db_conn_active?: number | null
   db_conn_idle?: number | null
   db_conn_waiting?: number | null

frontend/src/api/admin/settings.ts

@@ -50,6 +50,7 @@ export interface SystemSettings {
   ops_monitoring_enabled: boolean
   ops_realtime_monitoring_enabled: boolean
   ops_query_mode_default: 'auto' | 'raw' | 'preagg' | string
+  ops_metrics_interval_seconds: number
 }
 
 export interface UpdateSettingsRequest {
@@ -83,6 +84,7 @@ export interface UpdateSettingsRequest {
   ops_monitoring_enabled?: boolean
   ops_realtime_monitoring_enabled?: boolean
   ops_query_mode_default?: 'auto' | 'raw' | 'preagg' | string
+  ops_metrics_interval_seconds?: number
 }
 
 /**

frontend/src/i18n/locales/en.ts

@@ -1733,8 +1733,10 @@ export default {
       redis: 'Redis',
       goroutines: 'Goroutines',
       jobs: 'Jobs',
+      jobsHelp: 'Click “Details” to view job heartbeats and recent errors',
       active: 'active',
       idle: 'idle',
+      waiting: 'waiting',
       ok: 'ok',
       lastRun: 'last_run:',
       lastSuccess: 'last_success:',
@@ -1770,12 +1772,50 @@ export default {
       errorsSla: 'Errors (SLA scope)',
       upstreamExcl429529: 'Upstream (excl 429/529)',
       failedToLoadData: 'Failed to load ops data.',
+      failedToLoadOverview: 'Failed to load overview',
+      failedToLoadThroughputTrend: 'Failed to load throughput trend',
+      failedToLoadLatencyHistogram: 'Failed to load latency histogram',
+      failedToLoadErrorTrend: 'Failed to load error trend',
+      failedToLoadErrorDistribution: 'Failed to load error distribution',
+      failedToLoadErrorDetail: 'Failed to load error detail',
+      retryFailed: 'Retry failed',
       tpsK: 'TPS (K)',
       top: 'Top:',
       throughputTrend: 'Throughput Trend',
       latencyHistogram: 'Latency Histogram',
       errorTrend: 'Error Trend',
       errorDistribution: 'Error Distribution',
+      // Health Score & Diagnosis
+      health: 'Health',
+      healthCondition: 'Health Condition',
+      healthHelp: 'Overall system health score based on SLA, error rate, and resource usage',
+      healthyStatus: 'Healthy',
+      riskyStatus: 'At Risk',
+      idleStatus: 'Idle',
+      diagnosis: {
+        title: 'Smart Diagnosis',
+        footer: 'Automated diagnostic suggestions based on current metrics',
+        idle: 'System is currently idle',
+        idleImpact: 'No active traffic',
+        upstreamCritical: 'Upstream error rate critically high ({rate}%)',
+        upstreamCriticalImpact: 'May affect many user requests',
+        upstreamHigh: 'Upstream error rate elevated ({rate}%)',
+        upstreamHighImpact: 'Recommend checking upstream service status',
+        slaCritical: 'SLA critically below target ({sla}%)',
+        slaCriticalImpact: 'User experience severely degraded',
+        slaLow: 'SLA below target ({sla}%)',
+        slaLowImpact: 'Service quality needs attention',
+        errorHigh: 'Error rate too high ({rate}%)',
+        errorHighImpact: 'Many requests failing',
+        errorElevated: 'Error rate elevated ({rate}%)',
+        errorElevatedImpact: 'Recommend checking error logs',
+        healthCritical: 'Overall health score critically low ({score})',
+        healthCriticalImpact: 'Multiple metrics may be degraded; prioritize error rate and latency investigation',
+        healthLow: 'Overall health score low ({score})',
+        healthLowImpact: 'May indicate minor instability; monitor SLA and error rates',
+        healthy: 'All system metrics normal',
+        healthyImpact: 'Service running stable'
+      },
       // Error Log
       errorLog: {
         timeId: 'Time / ID',
@@ -2069,7 +2109,21 @@ export default {
         throughputTrend: 'Requests/QPS + Tokens/TPS in the selected window.',
         latencyHistogram: 'Latency distribution (duration_ms) for successful requests.',
         errorTrend: 'Error counts over time (SLA scope excludes business limits; upstream excludes 429/529).',
-        errorDistribution: 'Error distribution by status code.'
+        errorDistribution: 'Error distribution by status code.',
+        goroutines:
+          'Number of Go runtime goroutines (lightweight threads). There is no absolute “safe” number—use your historical baseline. Heuristic: <2k is common; 2k–8k watch; >8k plus rising queue/latency often suggests blocking/leaks.',
+        cpu: 'CPU usage percentage, showing system processor load.',
+        memory: 'Memory usage, including used and total available memory.',
+        db: 'Database connection pool status, including active, idle, and waiting connections.',
+        redis: 'Redis connection pool status, showing active and idle connections.',
+        jobs: 'Background job execution status, including last run time, success time, and error information.',
+        qps: 'Queries Per Second (QPS) and Tokens Per Second (TPS), real-time system throughput.',
+        tokens: 'Total number of tokens processed in the current time window.',
+        sla: 'Service Level Agreement success rate, excluding business limits (e.g., insufficient balance, quota exceeded).',
+        errors: 'Error statistics, including total errors, error rate, and upstream error rate.',
+        latency: 'Request latency statistics, including p50, p90, p95, p99 percentiles.',
+        ttft: 'Time To First Token, measuring the speed of first byte return in streaming responses.',
+        health: 'System health score (0-100), considering SLA, error rate, and resource usage.'
       },
       charts: {
         emptyRequest: 'No requests in this window.',
@@ -2183,7 +2237,9 @@ export default {
         queryModeHint: 'Default query mode for Ops Dashboard (auto/raw/preagg)',
         queryModeAuto: 'Auto (recommended)',
         queryModeRaw: 'Raw (most accurate, slower)',
-        queryModePreagg: 'Preagg (fastest, requires aggregation)'
+        queryModePreagg: 'Preagg (fastest, requires aggregation)',
+        metricsInterval: 'Metrics Collection Interval (seconds)',
+        metricsIntervalHint: 'How often to collect system/request metrics (60-3600 seconds)'
       },
       adminApiKey: {
         title: 'Admin API Key',

frontend/src/i18n/locales/zh.ts

@@ -1878,8 +1878,10 @@ export default {
       redis: 'Redis',
       goroutines: '协程',
       jobs: '后台任务',
+      jobsHelp: '点击“明细”查看任务心跳与报错信息',
       active: '活跃',
       idle: '空闲',
+      waiting: '等待',
       ok: '正常',
       lastRun: '最近运行',
       lastSuccess: '最近成功',
@@ -1898,8 +1900,8 @@ export default {
       errors: '错误',
       errorRate: '错误率：',
       upstreamRate: '上游错误率：',
-      latencyDuration: '延迟 (duration_ms)',
-      ttftLabel: 'TTFT (first_token_ms)',
+      latencyDuration: '延迟（毫秒）',
+      ttftLabel: '首字延迟（毫秒）',
       p50: 'p50',
       p90: 'p90',
       p95: 'p95',
@@ -1915,12 +1917,50 @@ export default {
       errorsSla: '错误（SLA范围）',
       upstreamExcl429529: '上游（排除429/529）',
       failedToLoadData: '加载运维数据失败',
-      tpsK: 'TPS (K)',
+      failedToLoadOverview: '加载概览数据失败',
+      failedToLoadThroughputTrend: '加载吞吐趋势失败',
+      failedToLoadLatencyHistogram: '加载延迟分布失败',
+      failedToLoadErrorTrend: '加载错误趋势失败',
+      failedToLoadErrorDistribution: '加载错误分布失败',
+      failedToLoadErrorDetail: '加载错误详情失败',
+      retryFailed: '重试失败',
+      tpsK: 'TPS（千）',
       top: '最高：',
       throughputTrend: '吞吐趋势',
       latencyHistogram: '延迟分布',
       errorTrend: '错误趋势',
       errorDistribution: '错误分布',
+      // Health Score & Diagnosis
+      health: '健康',
+      healthCondition: '健康状况',
+      healthHelp: '基于 SLA、错误率和资源使用情况的系统整体健康评分',
+      healthyStatus: '健康',
+      riskyStatus: '风险',
+      idleStatus: '待机',
+      diagnosis: {
+        title: '智能诊断',
+        footer: '基于当前指标的自动诊断建议',
+        idle: '系统当前处于待机状态',
+        idleImpact: '无活跃流量',
+        upstreamCritical: '上游错误率严重偏高 ({rate}%)',
+        upstreamCriticalImpact: '可能影响大量用户请求',
+        upstreamHigh: '上游错误率偏高 ({rate}%)',
+        upstreamHighImpact: '建议检查上游服务状态',
+        slaCritical: 'SLA 严重低于目标 ({sla}%)',
+        slaCriticalImpact: '用户体验严重受损',
+        slaLow: 'SLA 低于目标 ({sla}%)',
+        slaLowImpact: '需要关注服务质量',
+        errorHigh: '错误率过高 ({rate}%)',
+        errorHighImpact: '大量请求失败',
+        errorElevated: '错误率偏高 ({rate}%)',
+        errorElevatedImpact: '建议检查错误日志',
+        healthCritical: '综合健康评分过低 ({score})',
+        healthCriticalImpact: '多个指标可能同时异常，建议优先排查错误与延迟',
+        healthLow: '综合健康评分偏低 ({score})',
+        healthLowImpact: '可能存在轻度波动，建议关注 SLA 与错误率',
+        healthy: '所有系统指标正常',
+        healthyImpact: '服务运行稳定'
+      },
       // Error Log
       errorLog: {
         timeId: '时间 / ID',
@@ -2212,9 +2252,23 @@ export default {
       },
       tooltips: {
         throughputTrend: '当前窗口内的请求/QPS 与 token/TPS 趋势。',
-        latencyHistogram: '成功请求的延迟分布（duration_ms）。',
+        latencyHistogram: '成功请求的延迟分布（毫秒）。',
         errorTrend: '错误趋势（SLA 口径排除业务限制；上游错误率排除 429/529）。',
-        errorDistribution: '按状态码统计的错误分布。'
+        errorDistribution: '按状态码统计的错误分布。',
+        goroutines:
+          'Go 运行时的协程数量（轻量级线程）。没有绝对“安全值”，建议以历史基线为准。经验参考：<2000 常见；2000-8000 需关注；>8000 且伴随队列/延迟上升时，优先排查阻塞/泄漏。',
+        cpu: 'CPU 使用率，显示系统处理器的负载情况。',
+        memory: '内存使用率，包括已使用和总可用内存。',
+        db: '数据库连接池状态，包括活跃连接、空闲连接和等待连接数。',
+        redis: 'Redis 连接池状态，显示活跃和空闲的连接数。',
+        jobs: '后台任务执行状态，包括最近运行时间、成功时间和错误信息。',
+        qps: '每秒查询数（QPS）和每秒Token数（TPS），实时显示系统吞吐量。',
+        tokens: '当前时间窗口内处理的总Token数量。',
+        sla: '服务等级协议达成率，排除业务限制（如余额不足、配额超限）的成功请求占比。',
+        errors: '错误统计，包括总错误数、错误率和上游错误率。',
+        latency: '请求延迟统计，包括 p50、p90、p95、p99 等百分位数。',
+        ttft: '首Token延迟（Time To First Token），衡量流式响应的首字节返回速度。',
+        health: '系统健康评分（0-100），综合考虑 SLA、错误率和资源使用情况。'
       },
       charts: {
         emptyRequest: '该时间窗口内暂无请求。',
@@ -2320,14 +2374,16 @@ export default {
         description: '启用运维监控模块，用于排障与健康可视化',
         disabled: '运维监控已关闭',
         enabled: '启用运维监控',
-        enabledHint: '启用 Ops 运维监控模块（仅管理员可见）',
+        enabledHint: '启用运维监控模块（仅管理员可见）',
         realtimeEnabled: '启用实时监控',
-        realtimeEnabledHint: '启用实时 QPS/指标推送（WebSocket）',
+        realtimeEnabledHint: '启用实时请求速率和指标推送（WebSocket）',
         queryMode: '默认查询模式',
-        queryModeHint: 'Ops Dashboard 默认查询模式（auto/raw/preagg）',
+        queryModeHint: '运维监控默认查询模式（自动/原始/预聚合）',
         queryModeAuto: '自动（推荐）',
-        queryModeRaw: 'Raw（最准，但较慢）',
-        queryModePreagg: 'Preagg（最快，需预聚合）'
+        queryModeRaw: '原始（最准确，但较慢）',
+        queryModePreagg: '预聚合（最快，需预聚合）',
+        metricsInterval: '采集频率（秒）',
+        metricsIntervalHint: '系统/请求指标采集频率（60-3600 秒）'
       },
       adminApiKey: {
         title: '管理员 API Key',

frontend/src/views/admin/SettingsView.vue

@@ -715,6 +715,25 @@
                 class="w-[220px]"
               />
             </div>
+
+            <div v-if="form.ops_monitoring_enabled" class="mt-5 flex items-center justify-between">
+              <div>
+                <label class="font-medium text-gray-900 dark:text-white">{{
+                  t('admin.settings.opsMonitoring.metricsInterval')
+                }}</label>
+                <p class="text-sm text-gray-500 dark:text-gray-400">
+                  {{ t('admin.settings.opsMonitoring.metricsIntervalHint') }}
+                </p>
+              </div>
+              <input
+                v-model.number="form.ops_metrics_interval_seconds"
+                type="number"
+                min="60"
+                max="3600"
+                step="10"
+                class="w-[220px] rounded-lg border border-gray-300 bg-white px-3 py-2 text-sm text-gray-900 shadow-sm focus:border-primary-500 focus:outline-none focus:ring-1 focus:ring-primary-500 dark:border-dark-600 dark:bg-dark-800 dark:text-white"
+              />
+            </div>
           </div>
         </div>
 
@@ -824,7 +843,8 @@ const form = reactive<SettingsForm>({
   // Ops Monitoring (vNext)
   ops_monitoring_enabled: true,
   ops_realtime_monitoring_enabled: true,
-  ops_query_mode_default: 'auto'
+  ops_query_mode_default: 'auto',
+  ops_metrics_interval_seconds: 60
 })
 
 const opsQueryModeOptions = computed(() => [
@@ -922,7 +942,8 @@ async function saveSettings() {
       identity_patch_prompt: form.identity_patch_prompt,
       ops_monitoring_enabled: form.ops_monitoring_enabled,
       ops_realtime_monitoring_enabled: form.ops_realtime_monitoring_enabled,
-      ops_query_mode_default: form.ops_query_mode_default
+      ops_query_mode_default: form.ops_query_mode_default,
+      ops_metrics_interval_seconds: form.ops_metrics_interval_seconds
     }
     const updated = await adminAPI.settings.updateSettings(payload)
     Object.assign(form, updated)

frontend/src/views/admin/ops/OpsDashboard.vue

@@ -33,190 +33,6 @@
         @open-error-details="openErrorDetails"
       />
 
-      <!-- Overview -->
-      <div
-        v-if="opsEnabled && !(loading && !hasLoadedOnce)"
-        class="overflow-hidden rounded-3xl bg-white shadow-sm ring-1 ring-gray-900/5 dark:bg-dark-800 dark:ring-dark-700"
-      >
-        <div class="border-b border-gray-100 px-6 py-4 dark:border-dark-700">
-          <h3 class="text-base font-semibold text-gray-900 dark:text-white">{{ t('admin.ops.systemHealth') }}</h3>
-        </div>
-        <div class="p-6">
-          <div v-if="loadingOverview" class="flex items-center justify-center py-10">
-            <div class="h-8 w-8 animate-spin rounded-full border-b-2 border-primary-600"></div>
-          </div>
-
-          <div v-else-if="!overview?.system_metrics" class="py-6 text-sm text-gray-500 dark:text-gray-400">
-            {{ t('admin.ops.noSystemMetrics') }}
-          </div>
-
-          <div v-else class="space-y-6">
-            <div class="text-xs text-gray-500 dark:text-gray-400">
-              {{ t('admin.ops.collectedAt') }} {{ formatDateTime(overview.system_metrics.created_at) }} ({{ t('admin.ops.window') }}
-              {{ overview.system_metrics.window_minutes }}m)
-            </div>
-
-            <div class="grid grid-cols-1 gap-4 md:grid-cols-5">
-              <div class="rounded-xl bg-gray-50 p-4 dark:bg-dark-800/50">
-                <div class="text-xs text-gray-500 dark:text-gray-400">{{ t('admin.ops.cpu') }}</div>
-                <div class="mt-1 text-xl font-semibold text-gray-900 dark:text-white">
-                  {{ formatPercent0to100(overview.system_metrics.cpu_usage_percent) }}
-                </div>
-              </div>
-
-              <div class="rounded-xl bg-gray-50 p-4 dark:bg-dark-800/50">
-                <div class="text-xs text-gray-500 dark:text-gray-400">{{ t('admin.ops.memory') }}</div>
-                <div class="mt-1 text-xl font-semibold text-gray-900 dark:text-white">
-                  {{ formatPercent0to100(overview.system_metrics.memory_usage_percent) }}
-                </div>
-                <div class="mt-1 text-xs text-gray-500 dark:text-gray-400">
-                  {{ formatMBPair(overview.system_metrics.memory_used_mb, overview.system_metrics.memory_total_mb) }}
-                </div>
-              </div>
-
-              <div class="rounded-xl bg-gray-50 p-4 dark:bg-dark-800/50">
-                <div class="text-xs text-gray-500 dark:text-gray-400">{{ t('admin.ops.db') }}</div>
-                <div class="mt-1 text-xl font-semibold" :class="boolOkClass(overview.system_metrics.db_ok)">
-                  {{ boolOkLabel(overview.system_metrics.db_ok) }}
-                </div>
-                <div class="mt-1 text-xs text-gray-500 dark:text-gray-400">
-                  {{ t('admin.ops.active') }}: {{ overview.system_metrics.db_conn_active ?? '-' }}, {{ t('admin.ops.idle') }}:
-                  {{ overview.system_metrics.db_conn_idle ?? '-' }}
-                </div>
-              </div>
-
-              <div class="rounded-xl bg-gray-50 p-4 dark:bg-dark-800/50">
-                <div class="text-xs text-gray-500 dark:text-gray-400">{{ t('admin.ops.redis') }}</div>
-                <div class="mt-1 text-xl font-semibold" :class="boolOkClass(overview.system_metrics.redis_ok)">
-                  {{ boolOkLabel(overview.system_metrics.redis_ok) }}
-                </div>
-              </div>
-
-              <div class="rounded-xl bg-gray-50 p-4 dark:bg-dark-800/50">
-                <div class="text-xs text-gray-500 dark:text-gray-400">{{ t('admin.ops.goroutines') }}</div>
-                <div class="mt-1 text-xl font-semibold text-gray-900 dark:text-white">
-                  {{ overview.system_metrics.goroutine_count ?? '-' }}
-                </div>
-              </div>
-            </div>
-
-            <div v-if="overview?.job_heartbeats?.length" class="rounded-xl border border-gray-100 dark:border-dark-700">
-              <div class="border-b border-gray-100 px-4 py-3 text-sm font-semibold text-gray-900 dark:border-dark-700 dark:text-white">
-                {{ t('admin.ops.jobs') }}
-              </div>
-              <div class="divide-y divide-gray-100 dark:divide-dark-700">
-                <div
-                  v-for="job in overview.job_heartbeats"
-                  :key="job.job_name"
-                  class="flex flex-col gap-1 px-4 py-3 md:flex-row md:items-center md:justify-between"
-                >
-                  <div class="text-sm font-medium text-gray-900 dark:text-white">
-                    {{ job.job_name }}
-                  </div>
-                  <div class="text-xs text-gray-500 dark:text-gray-400">
-                    {{ t('admin.ops.lastRun') }}: {{ job.last_run_at ? formatDateTime(job.last_run_at) : '-' }} · {{ t('admin.ops.lastSuccess') }}:
-                    {{ job.last_success_at ? formatDateTime(job.last_success_at) : '-' }} ·
-                    <span v-if="job.last_error" class="text-rose-600 dark:text-rose-400">
-                      {{ t('admin.ops.lastError') }}: {{ job.last_error }}
-                    </span>
-                    <span v-else class="text-emerald-600 dark:text-emerald-400">{{ t('admin.ops.ok') }}</span>
-                  </div>
-                </div>
-              </div>
-            </div>
-          </div>
-        </div>
-      </div>
-
-      <div v-if="opsEnabled && !(loading && !hasLoadedOnce)" class="card">
-        <div class="border-b border-gray-100 px-6 py-4 dark:border-dark-700">
-          <h3 class="text-base font-semibold text-gray-900 dark:text-white">{{ t('admin.ops.overview') }}</h3>
-        </div>
-        <div class="p-6">
-          <div v-if="loadingOverview" class="flex items-center justify-center py-10">
-            <div class="h-8 w-8 animate-spin rounded-full border-b-2 border-primary-600"></div>
-          </div>
-
-          <div v-else-if="!overview" class="py-6 text-sm text-gray-500 dark:text-gray-400">
-            {{ t('admin.ops.noData') }}
-          </div>
-
-          <div v-else class="space-y-6">
-            <div class="grid grid-cols-1 gap-4 md:grid-cols-4">
-              <div class="rounded-xl bg-gray-50 p-4 dark:bg-dark-800/50">
-                <div class="text-xs text-gray-500 dark:text-gray-400">{{ t('admin.ops.requestsTotal') }}</div>
-                <div class="mt-1 text-xl font-semibold text-gray-900 dark:text-white">
-                  {{ formatInt(overview.request_count_total) }}
-                </div>
-                <div class="mt-1 text-xs text-gray-500 dark:text-gray-400">
-                  {{ t('admin.ops.slaScope') }} {{ formatInt(overview.request_count_sla) }}
-                </div>
-              </div>
-
-              <div class="rounded-xl bg-gray-50 p-4 dark:bg-dark-800/50">
-                <div class="text-xs text-gray-500 dark:text-gray-400">{{ t('admin.ops.tokens') }}</div>
-                <div class="mt-1 text-xl font-semibold text-gray-900 dark:text-white">
-                  {{ formatInt(overview.token_consumed) }}
-                </div>
-                <div class="mt-1 text-xs text-gray-500 dark:text-gray-400">
-                  {{ t('admin.ops.tps') }} {{ overview.tps.current }} ({{ t('admin.ops.peak') }} {{ overview.tps.peak }})
-                </div>
-              </div>
-
-              <div class="rounded-xl bg-gray-50 p-4 dark:bg-dark-800/50">
-                <div class="text-xs text-gray-500 dark:text-gray-400">{{ t('admin.ops.sla') }}</div>
-                <div class="mt-1 text-xl font-semibold text-gray-900 dark:text-white">
-                  {{ formatPercent(overview.sla) }}
-                </div>
-                <div class="mt-1 text-xs text-gray-500 dark:text-gray-400">
-                  {{ t('admin.ops.businessLimited') }}: {{ formatInt(overview.business_limited_count) }}
-                </div>
-              </div>
-
-              <div class="rounded-xl bg-gray-50 p-4 dark:bg-dark-800/50">
-                <div class="text-xs text-gray-500 dark:text-gray-400">{{ t('admin.ops.errors') }}</div>
-                <div class="mt-1 text-xs text-gray-600 dark:text-gray-300">
-                  {{ t('admin.ops.errorRate') }}: <span class="font-semibold">{{ formatPercent(overview.error_rate) }}</span>
-                </div>
-                <div class="mt-1 text-xs text-gray-600 dark:text-gray-300">
-                  {{ t('admin.ops.upstreamRate') }}: <span class="font-semibold">{{ formatPercent(overview.upstream_error_rate) }}</span>
-                </div>
-                <div class="mt-1 text-xs text-gray-500 dark:text-gray-400">
-                  429: {{ formatInt(overview.upstream_429_count) }} · 529:
-                  {{ formatInt(overview.upstream_529_count) }}
-                </div>
-              </div>
-            </div>
-
-            <div class="grid grid-cols-1 gap-4 md:grid-cols-2">
-              <div class="rounded-xl border border-gray-200 bg-white p-4 dark:border-dark-700 dark:bg-dark-900">
-                <div class="text-sm font-semibold text-gray-900 dark:text-white">{{ t('admin.ops.latencyDuration') }}</div>
-                <div class="mt-3 grid grid-cols-2 gap-2 text-xs text-gray-600 dark:text-gray-300 md:grid-cols-3">
-                  <div>{{ t('admin.ops.p50') }}: <span class="font-mono">{{ formatMs(overview.duration.p50_ms) }}</span></div>
-                  <div>{{ t('admin.ops.p90') }}: <span class="font-mono">{{ formatMs(overview.duration.p90_ms) }}</span></div>
-                  <div>{{ t('admin.ops.p95') }}: <span class="font-mono">{{ formatMs(overview.duration.p95_ms) }}</span></div>
-                  <div>{{ t('admin.ops.p99') }}: <span class="font-mono">{{ formatMs(overview.duration.p99_ms) }}</span></div>
-                  <div>{{ t('admin.ops.avg') }}: <span class="font-mono">{{ formatMs(overview.duration.avg_ms) }}</span></div>
-                  <div>{{ t('admin.ops.max') }}: <span class="font-mono">{{ formatMs(overview.duration.max_ms) }}</span></div>
-                </div>
-              </div>
-
-              <div class="rounded-xl border border-gray-200 bg-white p-4 dark:border-dark-700 dark:bg-dark-900">
-                <div class="text-sm font-semibold text-gray-900 dark:text-white">{{ t('admin.ops.ttftLabel') }}</div>
-                <div class="mt-3 grid grid-cols-2 gap-2 text-xs text-gray-600 dark:text-gray-300 md:grid-cols-3">
-                  <div>{{ t('admin.ops.p50') }}: <span class="font-mono">{{ formatMs(overview.ttft.p50_ms) }}</span></div>
-                  <div>{{ t('admin.ops.p90') }}: <span class="font-mono">{{ formatMs(overview.ttft.p90_ms) }}</span></div>
-                  <div>{{ t('admin.ops.p95') }}: <span class="font-mono">{{ formatMs(overview.ttft.p95_ms) }}</span></div>
-                  <div>{{ t('admin.ops.p99') }}: <span class="font-mono">{{ formatMs(overview.ttft.p99_ms) }}</span></div>
-                  <div>{{ t('admin.ops.avg') }}: <span class="font-mono">{{ formatMs(overview.ttft.avg_ms) }}</span></div>
-                  <div>{{ t('admin.ops.max') }}: <span class="font-mono">{{ formatMs(overview.ttft.max_ms) }}</span></div>
-                </div>
-              </div>
-            </div>
-          </div>
-        </div>
-      </div>
-
       <!-- Row: Concurrency + Throughput -->
       <div v-if="opsEnabled && !(loading && !hasLoadedOnce)" class="grid grid-cols-1 gap-6 lg:grid-cols-3">
         <div class="lg:col-span-1 min-h-[360px]">
@@ -308,7 +124,6 @@ import OpsLatencyChart from './components/OpsLatencyChart.vue'
 import OpsThroughputTrendChart from './components/OpsThroughputTrendChart.vue'
 import OpsAlertEventsCard from './components/OpsAlertEventsCard.vue'
 import OpsRequestDetailsModal, { type OpsRequestDetailsPreset } from './components/OpsRequestDetailsModal.vue'
-import { formatDateTime, formatNumberLocaleString } from '@/utils/format'
 
 const route = useRoute()
 const router = useRouter()
@@ -486,7 +301,6 @@ const syncQueryToRoute = useDebounceFn(async () => {
 }, 250)
 
 const overview = ref<OpsDashboardOverview | null>(null)
-const loadingOverview = ref(false)
 
 const throughputTrend = ref<OpsThroughputTrendResponse | null>(null)
 const loadingTrend = ref(false)
@@ -523,12 +337,15 @@ function handleThroughputSelectGroup(nextGroupId: number) {
   groupId.value = id
 }
 
-function handleOpenRequestDetails() {
-  requestDetailsPreset.value = {
+function handleOpenRequestDetails(preset?: OpsRequestDetailsPreset) {
+  const basePreset: OpsRequestDetailsPreset = {
     title: t('admin.ops.requestDetails.title'),
     kind: 'all',
     sort: 'created_at_desc'
   }
+
+  requestDetailsPreset.value = { ...basePreset, ...(preset ?? {}) }
+  if (!requestDetailsPreset.value.title) requestDetailsPreset.value.title = basePreset.title
   showRequestDetails.value = true
 }
 
@@ -573,46 +390,8 @@ function openError(id: number) {
   showErrorModal.value = true
 }
 
-function formatInt(v: number | null | undefined): string {
-  if (typeof v !== 'number') return '0'
-  return formatNumberLocaleString(v)
-}
-
-function formatPercent(v: number | null | undefined): string {
-  if (typeof v !== 'number') return '-'
-  return `${(v * 100).toFixed(2)}%`
-}
-
-function formatPercent0to100(v: number | null | undefined): string {
-  if (typeof v !== 'number') return '-'
-  return `${v.toFixed(1)}%`
-}
-
-function formatMBPair(used: number | null | undefined, total: number | null | undefined): string {
-  if (typeof used !== 'number' || typeof total !== 'number') return '-'
-  return `${formatNumberLocaleString(used)} / ${formatNumberLocaleString(total)} MB`
-}
-
-function boolOkLabel(v: boolean | null | undefined): string {
-  if (v === true) return 'OK'
-  if (v === false) return 'FAIL'
-  return '-'
-}
-
-function boolOkClass(v: boolean | null | undefined): string {
-  if (v === true) return 'text-emerald-600 dark:text-emerald-400'
-  if (v === false) return 'text-rose-600 dark:text-rose-400'
-  return 'text-gray-900 dark:text-white'
-}
-
-function formatMs(v: number | null | undefined): string {
-  if (v == null) return '-'
-  return `${v}ms`
-}
-
 async function refreshOverviewWithCancel(fetchSeq: number, signal: AbortSignal) {
   if (!opsEnabled.value) return
-  loadingOverview.value = true
   try {
     const data = await opsAPI.getDashboardOverview(
       {
@@ -628,11 +407,7 @@ async function refreshOverviewWithCancel(fetchSeq: number, signal: AbortSignal)
   } catch (err: any) {
     if (fetchSeq !== dashboardFetchSeq || isCanceledRequest(err)) return
     overview.value = null
-    appStore.showError(err?.message || 'Failed to load overview')
-  } finally {
-    if (fetchSeq === dashboardFetchSeq) {
-      loadingOverview.value = false
-    }
+    appStore.showError(err?.message || t('admin.ops.failedToLoadOverview'))
   }
 }
 
@@ -654,7 +429,7 @@ async function refreshThroughputTrendWithCancel(fetchSeq: number, signal: AbortS
   } catch (err: any) {
     if (fetchSeq !== dashboardFetchSeq || isCanceledRequest(err)) return
     throughputTrend.value = null
-    appStore.showError(err?.message || 'Failed to load throughput trend')
+    appStore.showError(err?.message || t('admin.ops.failedToLoadThroughputTrend'))
   } finally {
     if (fetchSeq === dashboardFetchSeq) {
       loadingTrend.value = false
@@ -680,7 +455,7 @@ async function refreshLatencyHistogramWithCancel(fetchSeq: number, signal: Abort
   } catch (err: any) {
     if (fetchSeq !== dashboardFetchSeq || isCanceledRequest(err)) return
     latencyHistogram.value = null
-    appStore.showError(err?.message || 'Failed to load latency histogram')
+    appStore.showError(err?.message || t('admin.ops.failedToLoadLatencyHistogram'))
   } finally {
     if (fetchSeq === dashboardFetchSeq) {
       loadingLatency.value = false
@@ -706,7 +481,7 @@ async function refreshErrorTrendWithCancel(fetchSeq: number, signal: AbortSignal
   } catch (err: any) {
     if (fetchSeq !== dashboardFetchSeq || isCanceledRequest(err)) return
     errorTrend.value = null
-    appStore.showError(err?.message || 'Failed to load error trend')
+    appStore.showError(err?.message || t('admin.ops.failedToLoadErrorTrend'))
   } finally {
     if (fetchSeq === dashboardFetchSeq) {
       loadingErrorTrend.value = false
@@ -732,7 +507,7 @@ async function refreshErrorDistributionWithCancel(fetchSeq: number, signal: Abor
   } catch (err: any) {
     if (fetchSeq !== dashboardFetchSeq || isCanceledRequest(err)) return
     errorDistribution.value = null
-    appStore.showError(err?.message || 'Failed to load error distribution')
+    appStore.showError(err?.message || t('admin.ops.failedToLoadErrorDistribution'))
   } finally {
     if (fetchSeq === dashboardFetchSeq) {
       loadingErrorDistribution.value = false

frontend/src/views/admin/ops/components/OpsErrorDetailModal.vue

@@ -286,7 +286,7 @@ async function fetchDetail(id: number) {
     }
   } catch (err: any) {
     detail.value = null
-    appStore.showError(err?.message || 'Failed to load error detail')
+    appStore.showError(err?.message || t('admin.ops.failedToLoadErrorDetail'))
   } finally {
     loading.value = false
   }
@@ -348,7 +348,7 @@ async function runConfirmedRetry() {
     const summary = res.status === 'succeeded' ? t('admin.ops.errorDetail.retrySuccess') : t('admin.ops.errorDetail.retryFailed')
     appStore.showSuccess(summary)
   } catch (err: any) {
-    appStore.showError(err?.message || 'Retry failed')
+    appStore.showError(err?.message || t('admin.ops.retryFailed'))
   } finally {
     retrying.value = false
   }