sidecar: add better message to user

Signed-off-by: vsoch <vsoch@users.noreply.github.com>

Author: vsoch

README.md

@@ -95,8 +95,7 @@ Admission control is a check that asks "Can we support a new hybrid queue?" wher
 
 ### What an IBM session costs
 
-IBM bills a dedicated session for wall clock time from the moment its first job starts until the session is closed or has sat idle for a minute. This includes idle time. In a shared gang there is always idle time between the scout's circuit finishing and the workers' circuits arriving, while the worker pods schedule,
-start and submit, and again after the last worker finishes before the scout releases. With dedicated mode that gap is billed at full rate and can come to about a minute per run. A batch session is billed only for time on the hardware, so the gap costs nothing. Thus, we choose to open batch sessions unless `FLUENCE_QRMI_SESSION_MODE=dedicated` is set. Use dedicated only when exclusive access is what you are measuring, and set a cost limit on the IBM instance first.
+IBM bills a dedicated session for wall clock time from the moment its first job starts until the session is closed or has sat idle for a minute. This includes idle time. In a shared gang there is always idle time between the scout's circuit finishing and the workers' circuits arriving, while the worker pods schedule, start and submit, and again after the last worker finishes before the scout releases. With dedicated mode that gap is billed at full rate and can come to about a minute per run. A batch session is billed only for time on the hardware, so the gap costs nothing. Thus, we choose to open batch sessions unless `FLUENCE_QRMI_SESSION_MODE=dedicated` is set. Use dedicated only when exclusive access is what you are measuring, and set a cost limit on the IBM instance first.
 
 The scheduler logs the graph when it starts, and for every match it logs the jobspec it sent, the allocation it got back, and how it read it, all prefixed with [fluence]. The webhook logs its environment contract at startup. You can look at logs to debug.
 

examples/qrmi-workload/sampler.py

@@ -1,17 +1,12 @@
 #!/usr/bin/env python3
 """A QRMI workload for a pod that fluence placed.
 
-fluence chose the backend and the webhook put its name in FLUXION_BACKEND.
+fluence chooses the backend and the webhook forwards via FLUXION_BACKEND.
 This acquires a session on it, runs a Bell circuit through the QRMI sampler,
 prints the counts, and releases the session. Without credentials it prints
 what it would need and exits, so the same pod works as a rehearsal.
-
-The session is opened in batch mode unless FLUENCE_QRMI_SESSION_MODE says
-dedicated. IBM bills a dedicated session for wall clock time from its first
-job until it closes or sits idle for a minute, so the gap between the scout's
-circuit and the workers' circuits is billed at full rate. A batch session is
-billed only for time on the hardware. Dedicated is for measuring exclusive
-access on purpose, and costs about a minute of idle time per run.
+The session is opened in batch mode unless FLUENCE_QRMI_SESSION_MODE is set
+to dedicated.
 """
 
 import argparse