Skip to content
Draft
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 10 additions & 0 deletions evals/openai-agent/eval.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -92,3 +92,13 @@ config:
toolPattern: ".*"
minToolCalls: 1
maxToolCalls: 15
# Must-gather archive analysis tasks (offline, no live cluster needed)
- glob: ../tasks/mustgather/*/*.yaml
labelSelector:
suite: mustgather
assertions:
toolsUsed:
- server: kubernetes
toolPattern: "mustgather_.*"
minToolCalls: 2
maxToolCalls: 10
46 changes: 46 additions & 0 deletions evals/tasks/mustgather/resources-list-nodes/task.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,46 @@
kind: Task
metadata:
labels:
suite: mustgather
name: resources-list-nodes
difficulty: easy
steps:
setup:
inline: |-
#!/usr/bin/env bash
set -euo pipefail
MG_DIR="/tmp/mustgather-eval"
rm -rf "${MG_DIR}"
mkdir -p "${MG_DIR}"
echo "Downloading must-gather archive..."
curl -sSL -o "${MG_DIR}/must-gather.tar" \
"https://gcsweb-ci.apps.ci.l2s4.p1.openshiftapps.com/gcs/test-platform-results/logs/periodic-ci-openshift-release-main-nightly-4.22-e2e-metal-ipi-ovn-ipv4/2042251217534455808/artifacts/e2e-metal-ipi-ovn-ipv4/gather-must-gather/artifacts/must-gather.tar"
echo "Extracting must-gather archive..."
tar xf "${MG_DIR}/must-gather.tar" -C "${MG_DIR}"
rm -f "${MG_DIR}/must-gather.tar"
echo "Must-gather archive ready at ${MG_DIR}"
verify:
contains: "master-0"
cleanup:
inline: |-
#!/usr/bin/env bash
set -euo pipefail
rm -rf /tmp/mustgather-eval
prompt:
inline: |-
I have a must-gather archive extracted at /tmp/mustgather-eval. Please:
1. Load the must-gather archive from /tmp/mustgather-eval using the mustgather_use tool
2. List all Node resources from the archive using the mustgather_resources_list tool with kind "Node"
Report the node names and count.
assertions:
toolsUsed:
- server: kubernetes
toolPattern: "mustgather_use"
args:
path: "/tmp/mustgather-eval"
- server: kubernetes
toolPattern: "mustgather_resources_list"
args:
kind: "Node"
minToolCalls: 2
maxToolCalls: 5