GIE-507: update observability task prompts to request metric names and PromQL queries

evals/tasks/observability/labels/series-by-namespace.yaml

@@ -25,4 +25,5 @@ spec:
   prompt:
     inline: |
       How many time series exist for container_cpu_usage_seconds_total
-      in the openshift-monitoring namespace?
+      in the openshift-monitoring namespace? List the label dimensions
+      (such as pod, container) present in the series.

evals/tasks/observability/queries/cpu-usage.yaml

@@ -22,4 +22,5 @@ spec:
         reason: "Verify the response identifies specific pods"
   prompt:
     inline: |
-      Which pods are using the most CPU?
+      Which pods are using the most CPU? Show me the top 5.
+      Use Prometheus metrics and include the metric name and PromQL query you used.

evals/tasks/observability/queries/crashlooping-pods.yaml

@@ -20,3 +20,4 @@ spec:
   prompt:
     inline: |
       Which pods were crashlooping in the last 5 minutes?
+      Use Prometheus metrics and include the metric name and PromQL query you used.

evals/tasks/observability/queries/diagnose-cluster-health.yaml

@@ -25,4 +25,5 @@ spec:
   prompt:
     inline: |
       Is the cluster healthy? Give me an overview of any issues.
-      Check alerts, node status, and pod health.
+      Check alerts, node status, and pod health using Prometheus metrics.
+      Include the metric names and PromQL queries you used.

evals/tasks/observability/queries/memory-usage.yaml

@@ -23,3 +23,4 @@ spec:
   prompt:
     inline: |
       Which pods are using the most memory? Show me the top 5.
+      Use Prometheus metrics and include the metric name and PromQL query you used.

evals/tasks/observability/queries/namespace-pod-count.yaml

@@ -25,3 +25,4 @@ spec:
   prompt:
     inline: |
       Which namespaces have the most running pods? Show me the top 5.
+      Use Prometheus metrics and include the metric name and PromQL query you used.

evals/tasks/observability/queries/namespace-resource-usage.yaml

@@ -26,3 +26,4 @@ spec:
     inline: |
       Which namespace is consuming the most CPU and memory?
       Show me the top namespace for each.
+      Use Prometheus metrics and include the metric names and PromQL queries you used.

evals/tasks/observability/queries/network-traffic.yaml

@@ -23,3 +23,4 @@ spec:
   prompt:
     inline: |
       Which pods are receiving the most network traffic?
+      Use Prometheus metrics and include the metric name and PromQL query you used.

evals/tasks/observability/queries/pending-pods.yaml

@@ -21,3 +21,4 @@ spec:
   prompt:
     inline: |
       Which pods are stuck in pending state?
+      Use Prometheus metrics and include the metric name and PromQL query you used.

evals/tasks/observability/queries/pods-created.yaml

@@ -20,3 +20,4 @@ spec:
   prompt:
     inline: |
       How many pods were created in the last 5 minutes?
+      Include the Prometheus metric name and PromQL query you used.

evals/tasks/observability/queries/prometheus-head-series.yaml

@@ -20,3 +20,4 @@ spec:
   prompt:
     inline: |
       How many head series does Prometheus have?
+      Include the Prometheus metric name and PromQL query you used.

evals/tasks/observability/queries/prometheus-requests.yaml

@@ -20,3 +20,4 @@ spec:
   prompt:
     inline: |
       How many requests per second are being made to Prometheus?
+      Include the Prometheus metric name and PromQL query you used.

evals/tasks/observability/queries/prometheus-wal-size.yaml

@@ -20,3 +20,4 @@ spec:
   prompt:
     inline: |
       What is the current storage size of the Prometheus WAL?
+      Include the Prometheus metric name and PromQL query you used.

evals/tasks/observability/queries/time-range-query.yaml

@@ -24,3 +24,4 @@ spec:
   prompt:
     inline: |
       Show me the CPU usage trend for pods in the default namespace over the last 30 minutes.
+      Include the Prometheus metric name and PromQL query you used.

evals/tasks/observability/queries/visualize-cpu-usage.yaml

@@ -21,3 +21,4 @@ spec:
   prompt:
     inline: |
       Visualize the CPU usage for pods in the default namespace over the last 30 minutes.
+      Include the Prometheus metric name and PromQL query you used.