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>

offline-backend-20260512/backend/app/gateway/app.py

@@ -27,6 +27,7 @@ from app.gateway.csrf_middleware import CSRFMiddleware
 from app.gateway.deps import langgraph_runtime
 from app.gateway.routers import (
     ai_writing,
+    admin_active_runs,
     admin_users,
     agents,
     artifacts,
@@ -488,6 +489,18 @@ _LEADERBOARD_SNAPSHOT_STARTUP_DELAY_SECONDS = _env_float(
     "ADMIN_LEADERBOARD_BACKGROUND_STARTUP_DELAY_SECONDS",
     60.0,
 )
+# Concurrency (system-pressure) sampler: how often to snapshot the in-flight run
+# count, and how long to keep samples (drives the admin 并发量 line chart, which
+# aggregates per minute/hour). Sampling is in-memory cheap (one tiny INSERT).
+_CONCURRENCY_SAMPLE_ENABLED = _env_bool("CONCURRENCY_SAMPLE_ENABLED", True)
+_CONCURRENCY_SAMPLE_INTERVAL_SECONDS = _env_float(
+    "CONCURRENCY_SAMPLE_INTERVAL_SECONDS",
+    15.0,
+)
+_CONCURRENCY_SAMPLE_RETENTION_HOURS = _env_float(
+    "CONCURRENCY_SAMPLE_RETENTION_HOURS",
+    168.0,  # 7 days
+)
 # Hour (local Beijing time, 0-23) after which the scheduler force-recomputes the
 # *previous* day's snapshot once, so records that landed near midnight are fully
 # captured. Default 1 ? "???? 1 ????????".
@@ -828,6 +841,58 @@ async def _leaderboard_snapshot_scheduler_loop() -> None:
         _release_singleton_lock(lock_handle)
 
 
+async def _concurrency_sampler_loop(app: FastAPI) -> None:
+    """Periodically record the in-flight run count for the admin pressure chart.
+
+    Runs in the gateway process, singleton-locked so only one worker samples.
+    Each tick records ``len(run_manager.list_active())`` and, roughly hourly,
+    purges samples older than the retention window. Best-effort throughout — a
+    failed tick is logged and the loop continues.
+    """
+    if not _CONCURRENCY_SAMPLE_ENABLED:
+        logger.info("Concurrency sampler disabled by CONCURRENCY_SAMPLE_ENABLED")
+        return
+
+    store = getattr(app.state, "concurrency_sample_store", None)
+    run_mgr = getattr(app.state, "run_manager", None)
+    if store is None or run_mgr is None:
+        logger.info("Concurrency sampler not started (no store / run manager — memory backend?)")
+        return
+
+    from deerflow.config.runtime_paths import runtime_home
+
+    lock_handle = _acquire_singleton_lock(runtime_home() / ".concurrency_sampler.lock")
+    if lock_handle is None:
+        logger.info("Concurrency sampler: another gateway worker holds the lock; this worker skips")
+        return
+
+    interval = max(1.0, _CONCURRENCY_SAMPLE_INTERVAL_SECONDS)
+    purge_every_ticks = max(1, int(3600 / interval))  # ~once per hour
+    logger.info("Concurrency sampler started: interval=%.1fs retention=%.1fh", interval, _CONCURRENCY_SAMPLE_RETENTION_HOURS)
+    ticks = 0
+    try:
+        while True:
+            try:
+                # Runtime toggle (admin can turn sampling off without a restart).
+                # mtime-cached read, so this is cheap every tick.
+                from deerflow.config.system_settings import get_concurrency_monitor_settings
+
+                if get_concurrency_monitor_settings().enabled:
+                    active = await run_mgr.list_active()
+                    await store.record(len(active))
+                    ticks += 1
+                    if ticks % purge_every_ticks == 0:
+                        from datetime import UTC, datetime, timedelta
+
+                        cutoff = datetime.now(UTC) - timedelta(hours=_CONCURRENCY_SAMPLE_RETENTION_HOURS)
+                        await store.purge_older_than(cutoff)
+            except Exception:
+                logger.exception("Concurrency sampler tick failed (non-fatal)")
+            await asyncio.sleep(interval)
+    finally:
+        _release_singleton_lock(lock_handle)
+
+
 def _warn_if_multi_worker() -> None:
     """?? uvicorn / gunicorn ? worker ???? ERROR ???
 
@@ -1044,6 +1109,13 @@ async def lifespan(app: FastAPI) -> AsyncGenerator[None, None]:
         except Exception:
             logger.exception("Leaderboard snapshot scheduler failed to start (non-fatal)")
 
+        # Concurrency (system-pressure) sampler — lightweight, singleton-locked,
+        # runtime-toggleable via system_settings.concurrency_monitor.enabled.
+        try:
+            app.state.concurrency_sampler_task = asyncio.create_task(_concurrency_sampler_loop(app))
+        except Exception:
+            logger.exception("Concurrency sampler failed to start (non-fatal)")
+
         # Start IM channel service if any channels are configured
         try:
             from app.channels.service import start_channel_service
@@ -1102,6 +1174,16 @@ async def lifespan(app: FastAPI) -> AsyncGenerator[None, None]:
             except Exception:
                 logger.exception("Leaderboard snapshot scheduler shutdown error")
 
+        concurrency_sampler_task = getattr(app.state, "concurrency_sampler_task", None)
+        if concurrency_sampler_task is not None:
+            concurrency_sampler_task.cancel()
+            try:
+                await concurrency_sampler_task
+            except asyncio.CancelledError:
+                pass
+            except Exception:
+                logger.exception("Concurrency sampler shutdown error")
+
         # ?? 7 ????AI ?? graph ???? checkpointer / in-flight task?
         # thread ??? LangGraph Server ? checkpointer ???lifespan ???
         # ``langgraph_runtime()`` ? contextmanager ???????????????
@@ -1434,6 +1516,8 @@ This gateway provides custom endpoints for models, MCP configuration, skills, an
     app.include_router(admin_users.router)
     app.include_router(admin_users.self_router)
 
+    app.include_router(admin_active_runs.router)
+
     # Admin tool / skill call metrics audit + export
     app.include_router(tool_metrics.router)