no-mistakes(review): Fix 5→6 node examples and parameterize restart commands
This commit is contained in:
@@ -31,7 +31,7 @@ Workers execute tasks on whatever infrastructure they're given — SSH to .6,
|
|||||||
## Why This Matters
|
## Why This Matters
|
||||||
|
|
||||||
Without enforced delegation, the manager consumes the full iteration budget
|
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
|
leaving no capacity for actual coordination. The result: context overflow
|
||||||
(59K tokens in system prompt), iteration exhaustion, and degraded response
|
(59K tokens in system prompt), iteration exhaustion, and degraded response
|
||||||
quality. This contract exists because I blew through my budget checking
|
quality. This contract exists because I blew through my budget checking
|
||||||
@@ -137,7 +137,7 @@ delegate_task(
|
|||||||
```
|
```
|
||||||
delegate_task(
|
delegate_task(
|
||||||
tasks=[
|
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"},
|
{"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",
|
"lane_id": "devops-check",
|
||||||
"worker": "syslog-devops",
|
"worker": "syslog-devops",
|
||||||
"goal": "Check all 5 Proxmox nodes",
|
"goal": "Check all 6 Proxmox nodes",
|
||||||
"status": "dispatched|completed|failed",
|
"status": "dispatched|completed|failed",
|
||||||
"output_file": "/tmp/node-report.md"
|
"output_file": "/tmp/node-report.md"
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -222,7 +222,7 @@ ssh root@<CT> "grep -E 'Finalized|Failed to finalize|Replied to' ~/.hermes/logs/
|
|||||||
|
|
||||||
| Condition | Action |
|
| 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 |
|
| No heartbeat in 10min | Same as above |
|
||||||
| `Failed to finalize` > 50% | Check PATCH API, Zulip server |
|
| `Failed to finalize` > 50% | Check PATCH API, Zulip server |
|
||||||
| Response empty/short | Check A2A endpoint / LiteLLM model |
|
| Response empty/short | Check A2A endpoint / LiteLLM model |
|
||||||
|
|||||||
Reference in New Issue
Block a user