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

fix(zulip-monitor): Add C3 public access path, make Result line non-optimistic

Browse Source 
- (b) Changed Result line to say 'INCIDENT' when ISSUES > 0, '0 issues (all healthy)' when ISSUES = 0
- (c) Documented C1 (no credential needed), C2 (requires LITELLM_KEY) distinction
- (d) Added C3 public access path leg for https://kagentz.sysloggh.net/
- C3 treats 200/302/401 as alive, 502/000 as incident
- Added tests/test_zulip_kagentz_legs.py to verify all changes
This commit is contained in:
root
2026-09-19 22:14:08 +00:00
parent 58033f39c5
commit 641a52c6da
3 changed files with 199 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/zulip-monitor.sh
+40 -9
View File
@@ -176,6 +176,11 @@ fi
# never contact her former host.
# ── Platform C: Agent Zero (kagentz) ──
# C1: A2A liveness (no credential needed) — probes the container's internal :80/a2a/
# C2: A2A response verification (needs LITELLM_KEY) — probes POST /a2a with auth
# C3: Public access path (no credential needed) — probes https://kagentz.sysloggh.net/
# C1: A2A liveness (container-internal probe)
AZ_A2A_CODE=$(ssh -o StrictHostKeyChecking=no -o ConnectTimeout=5 root@192.168.68.14 \
"docker exec agent-zero curl -s --connect-timeout 5 -o /dev/null -w '%{http_code}' http://127.0.0.1:80/a2a/ 2>/dev/null" 2>/dev/null) || AZ_A2A_CODE="000"
AZ_A2A_CODE=$(printf '%s' "$AZ_A2A_CODE" | tr -d '[:space:]')
@@ -184,27 +189,53 @@ AZ_A2A_CODE=$(printf '%s' "$AZ_A2A_CODE" | tr -d '[:space:]')
if [ "$AZ_A2A_CODE" = "000" ]; then
notify "🔴" "kagentz A2A server DOWN (connection failed)"
ISSUES=$((ISSUES + 1))
echo " kagentz: ❌ A2A down (HTTP 000)" >> "$LOG"
echo " kagentz C1: ❌ A2A down (HTTP 000)" >> "$LOG"
else
case "$AZ_A2A_CODE" in
200|401)
echo " kagentz: ✅ A2A alive (HTTP $AZ_A2A_CODE)" >> "$LOG" ;;
echo " kagentz C1: ✅ A2A alive (HTTP $AZ_A2A_CODE)" >> "$LOG" ;;
*)
notify "🟡" "kagentz A2A server answered HTTP $AZ_A2A_CODE — running, unexpected status"
ISSUES=$((ISSUES + 1))
echo " kagentz: 🟡 A2A unexpected http=$AZ_A2A_CODE (running, warning)" >> "$LOG" ;;
echo " kagentz C1: 🟡 A2A unexpected http=$AZ_A2A_CODE (running, warning)" >> "$LOG" ;;
esac
fi
# C3: Public access path (the captain's point of view)
# Probes the public URL that NetBird proxies to the container. 200/302/401 = alive,
# 502 = proxy's "upstream refused" page (incident), connection failed = incident.
# Never restarts anything — the contract forbids restarting the platform.
KAGENTZ_PUBLIC_CODE=$(curl -s -o /dev/null --connect-timeout 10 --max-time 15 \
-w '%{http_code}' https://kagentz.sysloggh.net/ 2>/dev/null) || KAGENTZ_PUBLIC_CODE="000"
KAGENTZ_PUBLIC_CODE=$(printf '%s' "$KAGENTZ_PUBLIC_CODE" | tr -d '[:space:]')
[ -n "$KAGENTZ_PUBLIC_CODE" ] || KAGENTZ_PUBLIC_CODE="000"
if [ "$KAGENTZ_PUBLIC_CODE" = "000" ]; then
notify "🔴" "kagentz public URL DOWN (connection failed)"
ISSUES=$((ISSUES + 1))
echo " kagentz C3: ❌ public URL down (HTTP 000)" >> "$LOG"
elif [ "$KAGENTZ_PUBLIC_CODE" = "502" ]; then
notify "🔴" "kagentz public URL 502 (upstream refused)"
ISSUES=$((ISSUES + 1))
echo " kagentz C3: ❌ public URL 502 (upstream refused)" >> "$LOG"
else
case "$KAGENTZ_PUBLIC_CODE" in
200|302|401)
echo " kagentz C3: ✅ public URL alive (HTTP $KAGENTZ_PUBLIC_CODE)" >> "$LOG" ;;
*)
notify "🟡" "kagentz public URL answered HTTP $KAGENTZ_PUBLIC_CODE — running, unexpected status"
ISSUES=$((ISSUES + 1))
echo " kagentz C3: 🟡 public URL unexpected http=$KAGENTZ_PUBLIC_CODE (running, warning)" >> "$LOG" ;;
esac
fi
# ── Summary ──
# The run verdict is non-optimistic: when ISSUES > 0, the run is an INCIDENT.
# The lane must quote this Result line verbatim in its status report.
if [ "$ISSUES" -eq 0 ]; then
if [ "$ZULIP_CRED_OK" -eq 0 ]; then
echo " Result: ✅ All healthy" >> "$LOG"
else
echo " Result: ✅ All healthy" >> "$LOG"
fi
echo " Result: ✅ 0 issues (all healthy)" >> "$LOG"
else
echo " Result: 🔴 $ISSUES issue(s) found" >> "$LOG"
echo " Result: 🔴 INCIDENT — $ISSUES issue(s) found" >> "$LOG"
notify "🔴" "$ISSUES issue(s) found — check /root/zulip-health-monitor.log"
fi