SyslogSolution/prose-contracts
7
0
Fork 0
Code Issues 2 Pull Requests Actions Packages Projects Releases Wiki Activity

Merged PR #50: fix/gpu-dense-docs
PR Pipeline — Authorize → Validate → Review → Merge / auth (push) Successful in 1s
Details
PR Pipeline — Authorize → Validate → Review → Merge / validate (push) Successful in 2s
Details
PR Pipeline — Authorize → Validate → Review → Merge / lint (push) Successful in 3s
Details
PR Pipeline — Authorize → Validate → Review → Merge / ai-review (push) Successful in 3s
Details
PR Pipeline — Authorize → Validate → Review → Merge / gate (push) Successful in 0s
Details

Browse Source
This commit is contained in:
root
2026-08-30 12:16:39 +00:00
parent 79af0ae7a3
commit 2dfc3e1530
15 changed files with 227 additions and 72 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/agent-health-check.py
+15 -13
View File
@@ -39,10 +39,6 @@ PVE_NODES = {
# Agent definitions: ct, host, user, pve_node, vault_key_name
AGENTS = {
"tanko": {"ct": 112, "host": "192.168.68.122", "user": "jerome", "pve": "amdpve", "vault_key": "TANKO_LITELLM_API_KEY", "runtime": "dsh"},
"abiba": {"ct": 100, "host": "192.168.68.24", "user": "root", "pve": "minipve", "vault_key": None}, # Pi agent + Mumuni Zulip, no vault key
"koby": {"ct": 111, "host": "192.168.68.129", "user": "root", "pve": "amdpve", "vault_key": "KOBY_LITELLM_API_KEY"},
"koonimo": {"ct": 113, "host": "192.168.68.114", "user": "root", "pve": "amdpve", "vault_key": "KOONIMO_LITELLM_API_KEY"},
}
GPU_HOSTS = {
@@ -238,6 +234,7 @@ def check_agents():
host = agent.get("host")
user = agent.get("user")
ct = agent["ct"]
report_only = agent.get("report_only", False)
# Tanko runs on DSH (DeepSeek Harness) since 2026-08-27 — it no longer runs a
# Hermes gateway, so skip the Hermes gateway/state/streaming/journal checks.
@@ -253,15 +250,20 @@ def check_agents():
print(f" ⬜ {name} (CT {ct}): cannot SSH — skip liveness check")
continue
# Gateway process
pid = ssh(host, "pgrep -f 'hermes_cli.main gateway run' | grep -v infisical | head -1", user=user)
if not pid:
# Try alternate binary name
pid = ssh(host, "pgrep -f 'hermes.*gateway' | grep -v infisical | grep -v bash | head -1", user=user)
if not pid:
print(f" ❌ {name}: GATEWAY NOT RUNNING")
FAIL.append(f"gateway-down:{name}")
continue
# ⛔ KOBY IS NEVER REPAIRED — diagnostic only
if report_only:
print(f" 🔍 {name}: REPORT-ONLY mode (diagnostic only, no repairs on .129)")
# Still check gateway status for reporting purposes
pid = ssh(host, "pgrep -f 'hermes_cli.main gateway run' | grep -v infisical | head -1", user=user)
if not pid:
pid = ssh(host, "pgrep -f 'hermes.*gateway' | grep -v infisical | grep -v bash | head -1", user=user)
if not pid:
print(f" ⚠️ {name}: GATEWAY NOT RUNNING (reported only)")
FAIL.append(f"gateway-down:{name}")
continue
else:
print(f" ✅ {name}: gateway running (pid={pid}, report-only mode)")
continue # Skip the rest of the check for Koby
# Gateway state file
state = ssh(host, "cat ~/.hermes/gateway_state.json 2>/dev/null", user=user)