no-mistakes(review): Fix 5→6 node examples and parameterize restart commands

This commit is contained in:
root
2026-07-20 17:19:18 +00:00
parent df836b115c
commit 35d09ba69a
2 changed files with 4 additions and 4 deletions
+3 -3
View File
@@ -31,7 +31,7 @@ Workers execute tasks on whatever infrastructure they're given — SSH to .6,
## Why This Matters
Without enforced delegation, the manager consumes the full iteration budget
(60 calls) on single-turn tasks — SSH to 5 nodes, check each VM, read logs —
(60 calls) on single-turn tasks — SSH to 6 nodes, check each VM, read logs —
leaving no capacity for actual coordination. The result: context overflow
(59K tokens in system prompt), iteration exhaustion, and degraded response
quality. This contract exists because I blew through my budget checking
@@ -137,7 +137,7 @@ delegate_task(
```
delegate_task(
tasks=[
{"goal": "Check all 5 Proxmox nodes for VM status", "context": "SSH to each node via 192.168.68.x, run 'qm list'"},
{"goal": "Check all 6 Proxmox nodes for VM status", "context": "SSH to each node via 192.168.68.x, run 'qm list'"},
{"goal": "Check Docker container health on .7/.116/.17", "context": "SSH to each host, check container status"},
]
)
@@ -191,7 +191,7 @@ Only verified results reach Kwame. Format per channel:
{
"lane_id": "devops-check",
"worker": "syslog-devops",
"goal": "Check all 5 Proxmox nodes",
"goal": "Check all 6 Proxmox nodes",
"status": "dispatched|completed|failed",
"output_file": "/tmp/node-report.md"
}
+1 -1
View File
@@ -222,7 +222,7 @@ ssh root@<CT> "grep -E 'Finalized|Failed to finalize|Replied to' ~/.hermes/logs/
| Condition | Action |
|-----------|--------|
| `zulip.state != "connected"` | `ssh root@<CT> "pkill -f 'gateway run'; sleep 2; hermes gateway restart"` |
| `zulip.state != "connected"` | Mumuni (PM2): `ssh root@<CT> "pm2 restart mumuni-zulip"`<br>Tanko (systemd): `ssh root@<CT> "hermes gateway restart"` |
| No heartbeat in 10min | Same as above |
| `Failed to finalize` > 50% | Check PATCH API, Zulip server |
| Response empty/short | Check A2A endpoint / LiteLLM model |