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

no-mistakes(review): Align zulip-monitor Tanko probe and B2/B3 criteria to dsh-web

Browse Source
This commit is contained in:
root
2026-09-08 12:10:58 +00:00
parent 5313e6b9ba
commit 4684ee64e0
2 changed files with 40 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/zulip-monitor.sh
+24 -13
View File
@@ -66,22 +66,33 @@ else
echo " Abiba: ✅ Connected (processed=$(echo "$PI_HEALTH" | python3 -c "import sys,json; d=json.load(sys.stdin); print(d.get('messages_processed',0))" 2>/dev/null))" >> "$LOG"
fi
# ── Platform B: Hermes (Tanko) ──
TANKO_STATE=$(ssh -o StrictHostKeyChecking=no -o ConnectTimeout=5 jerome@192.168.68.122 \
"cat ~/.hermes/gateway_state.json 2>/dev/null" 2>/dev/null || echo "{}")
TANKO_ZULIP=$(echo "$TANKO_STATE" | python3 -c "
import sys,json
d=json.load(sys.stdin)
p=d.get('platforms',{}).get('zulip',{})
print(p.get('state','unknown'))
" 2>/dev/null)
# ── Platform B: Tanko (DSH dsh-web on amdpve CT 112) ──
# Direct SSH to 192.168.68.122 is retired after the agent migrations. Tanko's
# Zulip gateway runs as the dsh-web systemd unit inside CT 112 on amdpve
# (192.168.68.15), reachable only via `pct exec`. The gateway binds
# 127.0.0.1:3080 loopback-only by design — a remote :3080 probe is refused and
# is NOT a fault.
TANKO_SVC=$(ssh -o StrictHostKeyChecking=no -o ConnectTimeout=5 root@192.168.68.15 \
"pct exec 112 -- systemctl is-active dsh-web" 2>/dev/null || echo "unknown")
TANKO_HTTP=$(ssh -o StrictHostKeyChecking=no -o ConnectTimeout=5 root@192.168.68.15 \
"pct exec 112 -- curl -s --connect-timeout 5 --max-time 10 -o /dev/null -w '%{http_code}' http://127.0.0.1:3080/" 2>/dev/null || echo "000")
if [ "$TANKO_ZULIP" != "connected" ]; then
notify "🔴" "Tanko (Hermes) Zulip state: $TANKO_ZULIP — needs restart"
if [ "$TANKO_SVC" != "active" ]; then
notify "🔴" "Tanko (DSH dsh-web) service state: $TANKO_SVC — needs restart"
ISSUES=$((ISSUES + 1))
echo " Tanko: ❌ state=$TANKO_ZULIP" >> "$LOG"
echo " Tanko: ❌ service=$TANKO_SVC" >> "$LOG"
elif [ "$TANKO_HTTP" = "000" ]; then
notify "🔴" "Tanko (DSH dsh-web) HTTP :3080 connection refused/timeout — needs restart"
ISSUES=$((ISSUES + 1))
echo " Tanko: ❌ http=000 (refused/timeout)" >> "$LOG"
else
echo " Tanko: ✅ Zulip connected" >> "$LOG"
case "$TANKO_HTTP" in
200|301|302|307|308|401|403)
echo " Tanko: ✅ service=active http=$TANKO_HTTP" >> "$LOG" ;;
*)
notify "🟡" "Tanko (DSH dsh-web) HTTP :3080 answered $TANKO_HTTP — running, unexpected status"
echo " Tanko: 🟡 service=active http=$TANKO_HTTP (running, warning)" >> "$LOG" ;;
esac
fi
# ── Platform B: Hermes (Mumuni) ──