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/active-runs.ts

@@ -0,0 +1,159 @@
+import { apiFetch } from "@/core/api";
+import { getBackendBaseURL } from "@/core/config";
+import { OptType, writeYLog } from "@/core/log/y-log";
+
+/** One in-flight model run as seen by the admin concurrency monitor. */
+export interface ActiveRunItem {
+  run_id: string;
+  thread_id: string;
+  status: string;
+  created_at: string;
+  elapsed_seconds: number;
+  user_id: string;
+  user_name: string;
+  agent_id: string;
+  agent_name: string;
+  thread_title: string;
+  kind: string;
+  multitask_strategy: string;
+}
+
+export interface ActiveRunsResponse {
+  count: number;
+  server_time: string;
+  runs: ActiveRunItem[];
+}
+
+export interface ConcurrencyPoint {
+  bucket: string;
+  peak: number;
+  avg: number;
+  samples: number;
+}
+
+export interface ConcurrencySeriesResponse {
+  granularity: string;
+  since: string;
+  until: string;
+  enabled: boolean;
+  points: ConcurrencyPoint[];
+}
+
+export interface TokenSpeedPoint {
+  bucket: string;
+  avg_tokens_per_sec: number;
+  min_tokens_per_sec: number;
+  max_tokens_per_sec: number;
+  samples: number;
+}
+
+export interface TokenSpeedSeriesResponse {
+  granularity: string;
+  since: string;
+  until: string;
+  points: TokenSpeedPoint[];
+}
+
+export type Granularity = "minute" | "hour";
+
+const base = () => `${getBackendBaseURL()}/api/admin/active-runs`;
+
+async function parse<T>(res: Response, what: string): Promise<T> {
+  if (!res.ok) {
+    const err = (await res.json().catch(() => ({}))) as { detail?: string };
+    throw new Error(err.detail ?? `${what} (HTTP ${res.status})`);
+  }
+  return res.json() as Promise<T>;
+}
+
+/** Live snapshot of all in-flight runs. Polled — intentionally NOT y-logged. */
+export async function loadActiveRuns(): Promise<ActiveRunsResponse> {
+  return parse<ActiveRunsResponse>(await apiFetch(base()), "Failed to load active runs");
+}
+
+/** Concurrency time-series (peak/avg per minute|hour). Polled — not y-logged. */
+export async function loadConcurrencySeries(
+  granularity: Granularity,
+  hours?: number,
+): Promise<ConcurrencySeriesResponse> {
+  const params = new URLSearchParams({ granularity });
+  if (hours) params.set("hours", String(hours));
+  return parse<ConcurrencySeriesResponse>(
+    await apiFetch(`${base()}/concurrency?${params}`),
+    "Failed to load concurrency series",
+  );
+}
+
+/** Token-speed time-series (tokens/sec per minute|hour). Polled — not y-logged. */
+export async function loadTokenSpeedSeries(
+  granularity: Granularity,
+  hours?: number,
+): Promise<TokenSpeedSeriesResponse> {
+  const params = new URLSearchParams({ granularity });
+  if (hours) params.set("hours", String(hours));
+  return parse<TokenSpeedSeriesResponse>(
+    await apiFetch(`${base()}/token-speed?${params}`),
+    "Failed to load token speed series",
+  );
+}
+
+/** Truly stop one in-flight run (cancels the live model stream). */
+export async function cancelActiveRun(runId: string): Promise<{ run_id: string; cancelled: boolean }> {
+  const url = `${base()}/${encodeURIComponent(runId)}/cancel`;
+  const result = await parse<{ run_id: string; cancelled: boolean }>(
+    await apiFetch(url, { method: "POST" }),
+    "Failed to cancel run",
+  );
+  writeYLog({
+    optType: OptType.other,
+    optDetail: "CM助手-全量-并发监控-停止对话调用",
+    url,
+    reqParam: { runId },
+    returnParam: result,
+  });
+  return result;
+}
+
+/** Stop every in-flight run at once. */
+export async function cancelAllActiveRuns(): Promise<{ cancelled_count: number }> {
+  const url = `${base()}/cancel-all`;
+  const result = await parse<{ cancelled_count: number }>(
+    await apiFetch(url, { method: "POST" }),
+    "Failed to cancel all runs",
+  );
+  writeYLog({
+    optType: OptType.other,
+    optDetail: "CM助手-全量-并发监控-全部停止",
+    url,
+    returnParam: result,
+  });
+  return result;
+}
+
+/** Read the background-sampler on/off switch. */
+export async function getMonitorSettings(): Promise<{ enabled: boolean }> {
+  return parse<{ enabled: boolean }>(
+    await apiFetch(`${base()}/settings`),
+    "Failed to load monitor settings",
+  );
+}
+
+/** Toggle the background concurrency sampler (admin only, no restart). */
+export async function updateMonitorSettings(enabled: boolean): Promise<{ enabled: boolean }> {
+  const url = `${base()}/settings`;
+  const result = await parse<{ enabled: boolean }>(
+    await apiFetch(url, {
+      method: "PUT",
+      headers: { "Content-Type": "application/json" },
+      body: JSON.stringify({ enabled }),
+    }),
+    "Failed to update monitor settings",
+  );
+  writeYLog({
+    optType: enabled ? OptType.enabled : OptType.disabled,
+    optDetail: `CM助手-全量-并发监控-${enabled ? "开启" : "关闭"}采样`,
+    url,
+    reqParam: { enabled },
+  });
+  return result;
+}

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: {

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

@@ -219,6 +219,19 @@ function isRunNotFoundError(message: string): boolean {
   return /run\s+[\w-]{8,}\s+not\s+found/i.test(message);
 }
 
+/**
+ * 同一会话上一轮还没生成完，又提交了新问题 → 后端返回 409
+ * 「already has an active run」。匹配 HTTP 409、英文兜底文案，或后端已中文化
+ * 的提示，统一映射成一句友好的中文。
+ */
+function isActiveRunConflictError(message: string): boolean {
+  return (
+    /\b409\b/.test(message) ||
+    /already has an active run/i.test(message) ||
+    /还在生成回答/.test(message)
+  );
+}
+
 function buildCurrentUserLabel(): string {
   const auth = getStoredAuth();
   if (!auth) {
@@ -555,6 +568,12 @@ export function useThreadStream({
         }
         return;
       }
+      // 上一轮还没结束又发了新问题（后端 409）：给一句明确的中文提示，而不是
+      // 把原始的英文/HTTP 错误抛给用户。
+      if (isActiveRunConflictError(message)) {
+        toast.info("当前对话还在生成回答，请等待本轮回复结束，或先点「停止」再发送新的问题。");
+        return;
+      }
       toast.error(message);
     },
     onFinish(state) {