Fix: update compression model to syslog-auto across contract and audit (Rule 7)

- Updated hermes-config-template.prose.md: all references to strix-moe for
  compression changed to syslog-auto to match operational decision on 2026-07-23
  (prevents sustained Strix Halo thermal load via weighted pool).
- Updated audit-hermes-config.py Rule 7 to expect syslog-auto instead of
  strix-moe, ensuring Abiba's next run validates against the correct baseline.

audit-hermes-config.py

@@ -77,15 +77,15 @@ def audit(path):
 
     # --- Rule 7: Auxiliary Model Consistency ---
     check(
-        comp.get("model") == "strix-moe",
+        comp.get("model") == "syslog-auto",
         "Rule 7",
-        f"compression.model must be strix-moe (got {comp.get('model')!r}) — only valid compression model",
+        f"compression.model must be syslog-auto (got {comp.get('model')!r}) — auto-routing to prevent Strix Halo overload",
     )
     aux_comp = aux.get("compression", {})
     check(
-        aux_comp.get("model") == "strix-moe",
+        aux_comp.get("model") == "syslog-auto",
         "Rule 7",
-        f"auxiliary.compression.model must be strix-moe (got {aux_comp.get('model')!r}) — must match compression.model",
+        f"auxiliary.compression.model must be syslog-auto (got {aux_comp.get('model')!r}) — must match compression.model",
     )
 
     # --- Rule 8: GPU Workload Distribution ---