iklim.co/Environment_Monitoring
3
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix(monitoring): prevent Vault crash and DNS null error

Browse Source 
- Vault: Wrap resp.json() in a try-except block to prevent JSONDecodeError when hitting an HTML error page (e.g. 502/503). This prevents the entire agent from crashing and missing heartbeats.
- Uptime Kuma DNS: Explicitly set dns_resolve_server to 1.1.1.1 in Python API payload to prevent Uptime Kuma backend from crashing on null properties.
This commit is contained in:
Murat ÖZDEMİR 2026-06-26 23:23:02 +03:00
parent 475eb762b9
commit 8a056a381b
2 changed files with 10 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
health-agent/scripts/setup_uptime_kuma.py
View File

@ -261,6 +261,7 @@ def setup_uptime_kuma(dry_run=False, only=None):
"hostname": hostname, "hostname": hostname,
"port": 53, "port": 53,
"accepted_statuscodes": ["200-299"], "accepted_statuscodes": ["200-299"],
"dns_resolve_server": "1.1.1.1",
"dns_resolve_type": dns_resolve_type, "dns_resolve_type": dns_resolve_type,
"interval": interval, "interval": interval,
} }
@ -280,6 +281,7 @@ def setup_uptime_kuma(dry_run=False, only=None):
"hostname": hostname, "hostname": hostname,
"port": 53, "port": 53,
"accepted_statuscodes": ["200-299"], "accepted_statuscodes": ["200-299"],
"dns_resolve_server": "1.1.1.1",
"dns_resolve_type": dns_resolve_type, "dns_resolve_type": dns_resolve_type,
"interval": interval, "interval": interval,
} }

13
health-agent/src/health_agent/checks/http.py
View File

@ -140,11 +140,14 @@ def check_vault():
max_ping = max(max_ping, ms) max_ping = max(max_ping, ms)
if resp is not None: if resp is not None:
data = resp.json() try:
if not data.get("sealed"): data = resp.json()
unsealed_count += 1 if not data.get("sealed"):
else: unsealed_count += 1
errors.append(f"{node} SEALED") else:
errors.append(f"{node} SEALED")
except Exception as e:
errors.append(f"{node} invalid response: {resp.status_code}")
else: else:
errors.append(f"{node} unreachable: {err}") errors.append(f"{node} unreachable: {err}")