Test ordered one-slot DFlash2 placements and preserve results

experiments/dflash2-medium-20260920/supervise.py

@@ -10,8 +10,12 @@ signal.signal(signal.SIGTERM,stop_signal); signal.signal(signal.SIGINT,stop_sign
 # Refuse if the known production state has changed, or if requests are active.
 for name in NAMES:
     assert run('docker','inspect',name,'--format','{{.State.Running}}').stdout.strip()=='true',name
-slots=json.loads(run('docker','exec',NAMES[-1],'curl','-fsS','http://127.0.0.1:8080/slots').stdout)
-assert not any(s['is_processing'] for s in slots),'Production request active'
+for attempt in range(60):
+    slots=json.loads(run('docker','exec',NAMES[-1],'curl','-fsS','http://127.0.0.1:8080/slots').stdout)
+    if not any(s['is_processing'] for s in slots): break
+    if attempt==0: print('WAIT production request active; no interruption',flush=True)
+    time.sleep(3)
+else: raise RuntimeError('Production remained busy for 180s; no services stopped')
 assert not run('docker','ps','-q','--filter','name=^mike-ai-dflash2-test$').stdout.strip(),'Existing experiment'
 child=None
 try:
@@ -36,5 +40,11 @@ finally:
     for _ in range(150):
         if run('docker','inspect',NAMES[-1],'--format','{{.State.Health.Status}}').stdout.strip()=='healthy': break
         time.sleep(2)
+    else: raise RuntimeError('Restored Medium did not become healthy')
     run('docker','start',NAMES[1],NAMES[0])
-    print('RESTORED existing medium/controller/router',flush=True)
+    for _ in range(60):
+        statuses=[run('docker','inspect',name,'--format','{{.State.Health.Status}}').stdout.strip() for name in NAMES[:2]]
+        if all(status=='healthy' for status in statuses): break
+        time.sleep(2)
+    else: raise RuntimeError('Restored router/controller did not become healthy')
+    print('RESTORED existing medium/controller/router; all healthy',flush=True)