From 1a1a109aa3f0229812f3fea7d08d156529451011 Mon Sep 17 00:00:00 2001
From: agent-company <agent@leeworks.dev>
Date: Fri, 29 May 2026 05:04:56 +0000
Subject: [PATCH] feat(monitoring): add APIDataCriticallyStale alert and fix
 APIDataStale for duration

- Fix APIDataStale 'for' duration from 5m to 30m (issue spec requires 30m)
- Add APIDataCriticallyStale alert at 60-day threshold (5184000s) with for: 1h
  and severity: critical

Both alerts fire on api_data_freshness_seconds metric for all three API jobs.
Existing APIHighErrorRate and APIHighLatency alerts are unmodified.
kustomize build flux/ passes.

Closes leeworks-agents/api-company#88
---
 flux/monitoring/prometheusrule-apis.yaml | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/flux/monitoring/prometheusrule-apis.yaml b/flux/monitoring/prometheusrule-apis.yaml
index 0f56111..d213d2e 100644
--- a/flux/monitoring/prometheusrule-apis.yaml
+++ b/flux/monitoring/prometheusrule-apis.yaml
@@ -71,7 +71,7 @@ spec:
         - alert: APIDataStale
           expr: |
             api_data_freshness_seconds{job=~"zip|holidays|air-quality"} > 2592000
-          for: 5m
+          for: 30m
           labels:
             severity: warning
             team: api-company
@@ -79,6 +79,20 @@ spec:
             summary: "Stale dataset on {{ $labels.job }} ({{ $labels.dataset }})"
             description: "{{ $labels.job }} dataset '{{ $labels.dataset }}' has not been re-seeded in {{ $value | humanizeDuration }} (threshold: 30 days). Re-seed required."
 
+        # -------------------------------------------------------------------
+        # APIDataCriticallyStale — data freshness > 60 days
+        # -------------------------------------------------------------------
+        - alert: APIDataCriticallyStale
+          expr: |
+            api_data_freshness_seconds{job=~"zip|holidays|air-quality"} > 5184000
+          for: 1h
+          labels:
+            severity: critical
+            team: api-company
+          annotations:
+            summary: "API data is critically stale on {{ $labels.job }}"
+            description: "{{ $labels.job }} data has not been re-seeded in more than 60 days ({{ $value | humanizeDuration }})"
+
         # -------------------------------------------------------------------
         # APIDown — any API job absent for 2 min
         # -------------------------------------------------------------------