feat(system): process heartbeat + /system/health, engine runs business fields (W9-I)

- process_heartbeat / process_heartbeat_sample (0034): api / worker / worker:agent / all
  upsert every 15s (event loop lag last/max, concurrency, running runs, SSE connections, memory)
- GET /system/health (admin): processes with 45s stale flag, SSE, DB latency/size/connections,
  disks (DATA_DIR / library roots / download dirs, cache thresholds), mount sentinel checks
  with IO timeout, engine pending/oldest/24h failure rate, schedules
- GET /system/health/history?hours=: bucketed lag / running / SSE series
- /engine/runs and /engine/runs/{id}: business {kind, refId, title, triggeredBy} joined from
  run input / task / agent_run / tasks_run_meta / outbox; businessKind / businessRefId filters
- docs/runbook/ops.md: field meanings and alert thresholds

Co-Authored-By: Claude Opus 5.5 <[email protected]>

apps/server/src/http/sse.ts

@@ -75,6 +75,12 @@ export class EventBus implements EventBusPort {
 
 const SINCE_PAGE = 500;
 
+/** 本进程当前打开的 SSE 流数(进程与健康页用;不含 JSON 补读请求) */
+let openStreams = 0;
+export function sseConnectionCount(): number {
+  return openStreams;
+}
+
 export interface SseOptions {
   bus: EventBusPort;
   keepaliveMs?: number;
@@ -135,6 +141,13 @@ export function sseRoutes({ bus, keepaliveMs = 15_000 }: SseOptions) {
     }
 
     return streamSSE(c, async (stream) => {
+      openStreams += 1;
+      let counted = true;
+      const release = () => {
+        if (counted) openStreams = Math.max(0, openStreams - 1);
+        counted = false;
+      };
+      stream.onAbort(release);
       const queue: EventEnvelope[] = [];
       let wake: (() => void) | null = null;
       // 先订阅再读缓冲,避免两者之间的事件丢失
@@ -185,6 +198,7 @@ export function sseRoutes({ bus, keepaliveMs = 15_000 }: SseOptions) {
       } finally {
         clearInterval(timer);
         unsubscribe();
+        release();
       }
     });
   }) as never);