Merge main and preserve dispatch backlog across monitor windows

Signed-off-by: Sy03 <1370724210@qq.com>

tests/engine/test_orchestrator_monitor.py

@@ -65,6 +65,31 @@ def test_note_loop_and_flush_json(tmp_path, monkeypatch):
     assert payload["replicas"]["stage=0,replica=0"]["inflight"] == [10]
 
 
+@pytest.mark.parametrize("drain", [False, True])
+def test_dispatch_backlog_carries_across_windows(tmp_path, monkeypatch, drain):
+    out_path = tmp_path / "orch_monitor.json"
+    monkeypatch.setenv("VLLM_OMNI_ORCH_MONITOR_PATH", str(out_path))
+    now = [0.0]
+    monkeypatch.setattr(time, "monotonic", lambda: now[0])
+    monitor = OrchestratorMonitor(replica_sampler=lambda: {})
+    monitor.set_dispatch_queue_size(3)
+    monitor.set_dispatch_queue_size(1)
+
+    now[0] = monitor_mod._WINDOW_S
+    monitor.note_loop(idle=False)
+    if drain:
+        monitor.set_dispatch_queue_size(0)
+    now[0] += monitor_mod._WINDOW_S
+    monitor.note_loop(idle=False)
+    now[0] += monitor_mod._WINDOW_S
+    monitor.flush()
+
+    windows = json.loads(out_path.read_text())["windows"]
+    remaining = 0 if drain else 1
+    assert windows["dispatch_queue_size"] == [1, remaining, remaining]
+    assert windows["dispatch_queue_high_water"] == [3, 1, remaining]
+
+
 def test_register_replica_backfills_prior_windows(tmp_path, monkeypatch):
     out_path = tmp_path / "orch_monitor.json"
     monkeypatch.setenv("VLLM_OMNI_ORCH_MONITOR_PATH", str(out_path))