18264 netapp_ontap_status: respect alert's suppression and acknowledgement

CMK-23741

Closes: #820
Change-Id: I3d00eef0f649b25edf502e2dee960bb4309c8581

Author: kbuettner

.werks/18264.md

@@ -0,0 +1,24 @@
+[//]: # (werk v2)
+# netapp_ontap_status: respect alert's suppression and acknowledgement
+
+key        | value
+---------- | ---
+date       | 2025-07-30T19:48:26+00:00
+version    | 2.4.0p36
+class      | feature
+edition    | cre
+component  | checks
+level      | 1
+compatible | yes
+
+This werk impacts those who monitor NetApp ONTAP systems.
+
+The Diagnosis Status service (netapp_ontap_status)
+was critical if at least one alert was present, regardless of its suppress or acknowledge status.
+
+This change modifies the mentioned service
+to consider alerts that are either acknowledged or suppressed on the NetApp side as OK.
+The service details will now also include the status of each alert
+(suppressed or acknowledged, if applicable) and the name of the suppressor or acknowledger.
+
+Credits for this change go to GitHub user @kbuettner.

cmk/plugins/netapp/agent_based/netapp_ontap_status.py

@@ -29,6 +29,15 @@
 # }
 
 
+def format_alert(alert):
+    s = alert.name
+    if alert.acknowledge:
+        s += f", acknowledged by {alert.acknowledger}"
+    if alert.suppress:
+        s += f", suppressed by {alert.suppressor}"
+    return s
+
+
 def parse_netapp_api_status(string_table: StringTable) -> Section:
     return [
         alert for line in string_table for alert in [models.AlertModel.model_validate_json(line[0])]
@@ -46,14 +55,25 @@ def discovery_netapp_ontap_status(section: Section) -> DiscoveryResult:
 
 
 def check_netapp_ontap_status(section: Section) -> CheckResult:
-    """
-    Status is considered OK if there are no alerts
-    """
-
     if not section:
-        yield Result(state=State.OK, summary="Status: OK")
+        yield Result(state=State.OK, summary="No alerts present")
+        return
+
+    handled_alerts = [alert for alert in section if alert.acknowledge or alert.suppress]
+    unhandled_alerts = [alert for alert in section if alert not in handled_alerts]
+    # show the unhandled alerts first
+    details = "\n".join(format_alert(alert) for alert in unhandled_alerts + handled_alerts)
+
+    if unhandled_alerts:
+        yield Result(
+            state=State.CRIT, summary="Unhandled alerts present, see details", details=details
+        )
     else:
-        yield Result(state=State.CRIT, summary="Status: Alerts present")
+        yield Result(
+            state=State.OK,
+            summary="Alerts present, but all acknowledged or suppressed, see details",
+            details=details,
+        )
 
 
 check_plugin_netapp_ontap_status = CheckPlugin(

cmk/plugins/netapp/models.py

@@ -581,10 +581,15 @@ class ShelfPsuModel(ShelfObjectModel):
 
 class AlertModel(BaseModel):
     """
-    cfr: https://docs.netapp.com/us-en/ontap-restmap-9141//diagnosis.html#diagnosis-alert-get
+    https://docs.netapp.com/us-en/ontap-restmap-9141//diagnosis.html#diagnosis-alert-get
     """
 
     name: str
+    # this fields should always be present since ONTAP v 9.8 but better be safe than sorry...
+    acknowledge: bool = False
+    acknowledger: str = ""
+    suppress: bool = False
+    suppressor: str = ""
 
 
 class NtpPeerStatusModel(BaseModel):

tests/unit/cmk/plugins/netapp/test_netapp_ontap_status.py

@@ -21,15 +21,60 @@ class AlertModelFactory(ModelFactory):
     "alerts_models, expected_result",
     [
         pytest.param(
-            [AlertModelFactory.build(name="alert1"), AlertModelFactory.build(name="alert2")],
-            [Result(state=State.CRIT, summary="Status: Alerts present")],
+            [
+                AlertModelFactory.build(name="alert1", acknowledge=False, suppress=False),
+                AlertModelFactory.build(name="alert2", acknowledge=False, suppress=False),
+            ],
+            [
+                Result(
+                    state=State.CRIT,
+                    summary="Unhandled alerts present, see details",
+                    details="alert1\nalert2",
+                )
+            ],
             id="alerts present",
         ),
         pytest.param(
             [],
-            [Result(state=State.OK, summary="Status: OK")],
+            [Result(state=State.OK, summary="No alerts present")],
             id="no alerts present",
         ),
+        pytest.param(
+            [
+                AlertModelFactory.build(
+                    name="alert1", acknowledge=True, acknowledger="hhirsch", suppress=False
+                ),
+                AlertModelFactory.build(
+                    name="alert2", acknowledge=False, suppress=True, suppressor="hhirsch"
+                ),
+            ],
+            [
+                Result(
+                    state=State.OK,
+                    summary="Alerts present, but all acknowledged or suppressed, see details",
+                    details="alert1, acknowledged by hhirsch\nalert2, suppressed by hhirsch",
+                )
+            ],
+            id="alerts suppressed",
+        ),
+        pytest.param(
+            [
+                AlertModelFactory.build(
+                    name="alert2", acknowledge=False, suppress=True, suppressor="hhirsch"
+                ),
+                AlertModelFactory.build(
+                    name="alert1", acknowledge=False, acknowledger="hhirsch", suppress=False
+                ),
+            ],
+            [
+                Result(
+                    state=State.CRIT,
+                    summary="Unhandled alerts present, see details",
+                    details="alert1\nalert2, suppressed by hhirsch",
+                )
+            ],
+            id="one alert not suppressed (show it first)",
+        ),
     ],
 )
 def test_check_netapp_ontap_status(