feat(监控): 管理员排行榜实时并发监控 + 真正停止对话 + 409 中文化

- 排行榜页顶部新增「实时并发监控」面板（admin-only）：当前并发大模型调用数 +
  调用列表（用户/智能体/类型/已运行时长），每行「停止」+「全部停止」经
  RunManager.cancel 真正中断 LLM 流式调用，减轻大模型压力
- 并发量折线图（峰值/均值，按分钟/小时）：新增轻量后台采样器写入新表
  concurrency_samples（create_all 自动建表），可按分/时聚合
- 大模型出字速度折线图（tokens/秒，按分钟/小时）：复用 llm_call_metrics 聚合，
  便于定位是模型/供应商慢
- 后台采样可开关、默认关闭(opt-in)、运行时切换免重启、对线上零影响
  （单条极小 INSERT、保留期清理、查询有上限、全程 best-effort）
- 409 中文化：上一轮未结束又发新问题时返回中文提示，前端 onError 友好映射

后端：runtime/runs/manager.py(list_active)、persistence/concurrency(新模块)、
config/system_settings(ConcurrencyMonitorSettings)、gateway/routers/admin_active_runs、
app.py(采样后台任务)、services.py(409)。前端：core/admin/{active-runs,hooks}、
components/workspace/admin/concurrency-monitor、AdminUserLeaderboardPage、threads/hooks。

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

frontend-web/src/core/admin/hooks.ts

@@ -17,6 +17,96 @@ import {
   updateAdminV1Fact,
   updateAdminV1Section,
 } from "./api";
+import {
+  cancelActiveRun,
+  cancelAllActiveRuns,
+  getMonitorSettings,
+  loadActiveRuns,
+  loadConcurrencySeries,
+  loadTokenSpeedSeries,
+  updateMonitorSettings,
+  type Granularity,
+} from "./active-runs";
+
+// ── 实时并发监控 (admin) ─────────────────────────────────────────────────────
+
+/** Live snapshot of in-flight runs. Polls every `intervalMs` while `enabled`. */
+export function useActiveRuns(enabled = true, intervalMs = 4000) {
+  return useQuery({
+    queryKey: ["admin-active-runs", "live"],
+    queryFn: loadActiveRuns,
+    enabled,
+    refetchInterval: enabled ? intervalMs : false,
+    refetchOnWindowFocus: false,
+  });
+}
+
+/** 并发量时序 (peak/avg per minute|hour). */
+export function useConcurrencySeries(
+  granularity: Granularity,
+  hours: number | undefined,
+  enabled = true,
+  intervalMs = 15000,
+) {
+  return useQuery({
+    queryKey: ["admin-active-runs", "concurrency", granularity, hours ?? null],
+    queryFn: () => loadConcurrencySeries(granularity, hours),
+    enabled,
+    refetchInterval: enabled ? intervalMs : false,
+    refetchOnWindowFocus: false,
+  });
+}
+
+/** 大模型 token 出字速度时序 (tokens/sec per minute|hour). */
+export function useTokenSpeedSeries(
+  granularity: Granularity,
+  hours: number | undefined,
+  enabled = true,
+  intervalMs = 15000,
+) {
+  return useQuery({
+    queryKey: ["admin-active-runs", "token-speed", granularity, hours ?? null],
+    queryFn: () => loadTokenSpeedSeries(granularity, hours),
+    enabled,
+    refetchInterval: enabled ? intervalMs : false,
+    refetchOnWindowFocus: false,
+  });
+}
+
+export function useCancelActiveRun() {
+  const qc = useQueryClient();
+  return useMutation({
+    mutationFn: (runId: string) => cancelActiveRun(runId),
+    onSuccess: () => qc.invalidateQueries({ queryKey: ["admin-active-runs", "live"] }),
+  });
+}
+
+export function useCancelAllActiveRuns() {
+  const qc = useQueryClient();
+  return useMutation({
+    mutationFn: () => cancelAllActiveRuns(),
+    onSuccess: () => qc.invalidateQueries({ queryKey: ["admin-active-runs", "live"] }),
+  });
+}
+
+export function useMonitorSettings(enabled = true) {
+  return useQuery({
+    queryKey: ["admin-active-runs", "settings"],
+    queryFn: getMonitorSettings,
+    enabled,
+    refetchOnWindowFocus: false,
+  });
+}
+
+export function useUpdateMonitorSettings() {
+  const qc = useQueryClient();
+  return useMutation({
+    mutationFn: (nextEnabled: boolean) => updateMonitorSettings(nextEnabled),
+    onSuccess: (data) => {
+      qc.setQueryData(["admin-active-runs", "settings"], data);
+    },
+  });
+}
 
 export function useUserLeaderboard(
   range: {