Przeglądaj źródła

docs(agents): warn that cluster may be serving live before stop/power off

A model (often the agent itself) may be running on the cluster at any
time. A stray `stop` or `power off` has killed running agents mid-task
before. Document the safety check: run `health` and confirm with the
user before any destructive command; logs/health/doctor/dry-runs are
always safe.
Alexander Korolev 3 miesięcy temu
rodzic
commit
4767f6fe4d
1 zmienionych plików z 7 dodań i 0 usunięć
  1. 7 0
      AGENTS.md

+ 7 - 0
AGENTS.md

@@ -22,6 +22,13 @@ serve/stop/logs/health/doctor/exec/power/tmux/init-host-keys
 
 Cluster: exact name, prefix (`4`→`4nodes-switch`), or `auto` (smallest with NCCL + matching `required_nodes`).
 
+> ⚠️ **Cluster may be serving live traffic.** A model (often the one serving this
+> very agent) may be running on the cluster at any time. Before running `stop`,
+> `power off`, or `power switch`, ALWAYS first run `health` and confirm with the
+> user that the cluster is not serving before proceeding. Do NOT assume the
+> cluster is idle — a stray `stop`/`power off` has killed running agents mid-task
+> before. `logs`, `health`, `doctor`, and dry-runs (`-d`) are always safe.
+
 ## Recipe format (`recipes/<name>/recipe.toml`)
 
 ```toml