fix(daily-infra-report): resolve PVE token from env; make a dead probe non-silent
PR Pipeline — Authorize → Validate → Review → Merge / auth (pull_request) Successful in 4s
PR Pipeline — Authorize → Validate → Review → Merge / validate (pull_request) Successful in 5s
PR Pipeline — Authorize → Validate → Review → Merge / lint (pull_request) Failing after 10s
PR Pipeline — Authorize → Validate → Review → Merge / ai-review (pull_request) Successful in 9s
PR Pipeline — Authorize → Validate → Review → Merge / gate (pull_request) Skipped

The Proxmox leg of the daily digest has been reporting NOTHING while exiting 0.

Root cause: the auth header was a literal placeholder string,

    AUTH = "Authorization: PVEAPIToken=«vault: infrastructure/production PVE_API_TOKEN»"

which was sent verbatim. The API rejected it, pve_get() returned None, and the
report rendered node_count=0 / nodes_online=0 with pve_probe_status='unreachable'
while still exiting 0. A monitoring gap that looks like a healthy run.

Also: the vault key is PVE_TOKEN, not PVE_API_TOKEN, so even reading os.environ
by the old name would not have found it.

Fixes:
* pve_auth() resolves the token at call time from PVE_TOKEN (injected by
  'infisical run --env=prod'). Nothing is hardcoded; a missing token raises.
* pve_get() builds the command inside its try block, so a missing token degrades
  to None instead of escaping as an unhandled exception.
* PROBE_FAILURES records an unreachable node/resources probe. Probe failures are
  deliberately separate from DEGRADED_LEGS: a missing credential stays exit 0
  (existing intent), but a probe with no data now exits 1 in both the report and
  --json paths, so it cannot pass unnoticed.

Measured effect on the live host: pve_probe_status unreachable -> ok,
node_count 0 -> 5, nodes_online 0 -> 5, total_vms 0 -> 22, running_vms 0 -> 22.

Tests: 4 new regression tests; all 4 fail against the pre-fix script and pass
after, and the 3 pre-existing tests still pass (7/7).

Not fixed here (needs the captain): the email leg fails with
'534 5.7.9 Application-specific password required' - EMAIL_PASSWORD in the vault
is not a valid Gmail app password for jtabiri@gmail.com. That is a credential
action, not a code change.
This commit is contained in:
root
2026-09-25 10:34:07 +00:00
parent 5409dfd73a
commit cdc7ad2c79
2 changed files with 111 additions and 3 deletions
+38 -3
View File
@@ -16,7 +16,20 @@ from email.mime.text import MIMEText
from email.mime.multipart import MIMEMultipart
PVE = "https://192.168.68.12:8006"
AUTH = "Authorization: PVEAPIToken=«vault: infrastructure/production PVE_API_TOKEN»"
def pve_auth():
"""PVE API auth header, resolved at call time from the injected environment.
The token is injected by ``infisical run --env=prod`` as ``PVE_TOKEN``
(format ``user@realm!tokenid=secret``). It must never be hardcoded: a
placeholder literal authenticates as nobody, which is how this probe
reported zero nodes while still exiting 0. Raise loudly instead.
"""
token = os.environ.get("PVE_TOKEN")
if not token:
raise RuntimeError("PVE_TOKEN is not set (run under `infisical run --env=prod`)")
return f"Authorization: PVEAPIToken={token}"
# ── Shared credentials —─
@@ -29,6 +42,12 @@ ZULIP_EMAIL = "abiba-bot@chat.sysloggh.net"
ZULIP_AUTH = None
DEGRADED_LEGS = []
# Probe failures are different from degraded legs. A missing credential is an
# expected, survivable state (stays exit 0). A probe that cannot reach the API
# means the report has NO data for that section, which is a monitoring loss and
# must exit non-zero so it cannot pass unnoticed.
PROBE_FAILURES = []
LITELLM_PUBLIC = "https://litellm.sysloggh.net"
LITELLM_BACKEND = "192.168.68.116"
AUTH_HOST = "192.168.68.11"
@@ -48,9 +67,13 @@ TIME_STR = NOW.strftime("%Y-%m-%d %H:%M UTC")
# ── Helpers ──
def pve_get(path):
"""Fetch PVE API data. Returns list on success, None on error (to distinguish from empty list)."""
cmd = f'curl -sk --connect-timeout 10 "{PVE}{path}" -H "{AUTH}"'
"""Fetch PVE API data. Returns list on success, None on error (to distinguish from empty list).
A missing PVE_TOKEN is caught here and reported as ``None`` so the caller
records a probe failure; it must not escape as an unhandled exception.
"""
try:
cmd = f'curl -sk --connect-timeout 10 "{PVE}{path}" -H "{pve_auth()}"'
r = subprocess.run(cmd, shell=True, capture_output=True, text=True, timeout=12)
if r.returncode != 0:
return None
@@ -118,6 +141,7 @@ def collect():
report["node_count"] = 0
report["nodes_online"] = 0
report["pve_probe_status"] = "unreachable"
PROBE_FAILURES.append("proxmox: node list unreachable (PVE_TOKEN missing or API down)")
else:
report["nodes"] = {n["node"]: {
"cpu_pct": round(n.get('cpu',0)*100, 1),
@@ -137,6 +161,7 @@ def collect():
if resources is None:
vms = []
report["resources_probe_status"] = "unreachable"
PROBE_FAILURES.append("proxmox: cluster resources unreachable")
else:
vms = [r for r in resources if r.get("type") in ("qemu","lxc")]
report["resources_probe_status"] = "ok"
@@ -700,6 +725,10 @@ if __name__ == "__main__":
if "--json" in sys.argv:
print(json.dumps(report, indent=2, default=str))
if PROBE_FAILURES:
for leg in PROBE_FAILURES:
print(f"PROBE FAILURE: {leg}", file=sys.stderr)
sys.exit(1)
sys.exit(0)
print(" Building dashboard...")
@@ -737,3 +766,9 @@ if __name__ == "__main__":
for k,v in report.get('agents',{}).items():
agent_parts.append(f"{k}:{v.get('gateway_state',v.get('pm2_status','?'))}")
print(f" Agents: {', '.join(agent_parts)}")
if PROBE_FAILURES:
print(f"\n❌ Probe failures ({len(PROBE_FAILURES)}):")
for leg in PROBE_FAILURES:
print(f" - {leg}")
sys.exit(1)