Skip to content
Open
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
Original file line number Diff line number Diff line change
Expand Up @@ -67,6 +67,8 @@ tests:
env:
EVAL_CASES: case-003
EVAL_CONFIG: plugins/ci/evals/eval-payload-analysis.yaml
EVAL_HARNESS_REF: eval-stop-guard-hook
EVAL_HARNESS_REPO: https://github.com/stbenjam/agent-eval-harness.git
EVAL_MAX_TURNS: "250"
EVAL_MODEL: claude-opus-4-6
EVAL_SETUP_SCRIPT: plugins/ci/evals/scripts/extract-payload-analysis-snapshots.sh
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -109,8 +109,11 @@ fi
echo ""
echo "=== Installing plugins ==="
EVAL_HARNESS_DIR="/tmp/agent-eval-harness"
git clone --depth 1 https://github.com/opendatahub-io/agent-eval-harness.git "${EVAL_HARNESS_DIR}"
echo "agent-eval-harness cloned."
# EVAL_HARNESS_REPO / EVAL_HARNESS_REF let a PR rehearse the eval against a
# not-yet-merged branch of the harness. They default to the released main.
EVAL_HARNESS_REPO="${EVAL_HARNESS_REPO:-https://github.com/opendatahub-io/agent-eval-harness.git}"
git clone --depth 1 ${EVAL_HARNESS_REF:+--branch "${EVAL_HARNESS_REF}"} "${EVAL_HARNESS_REPO}" "${EVAL_HARNESS_DIR}"
echo "agent-eval-harness cloned from ${EVAL_HARNESS_REPO} (ref: ${EVAL_HARNESS_REF:-default})."

# -----------------------------------------------------------------------
# Run optional setup script (e.g. extract snapshots, populate fixtures)
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,10 @@ ref:
name: claude-payload-agent-github-token
mount_path: /var/run/github-token
env:
- name: EVAL_HARNESS_REPO
default: "https://github.com/opendatahub-io/agent-eval-harness.git"
- name: EVAL_HARNESS_REF
default: ""
- name: EVAL_CONFIG
default: "eval.yaml"
- name: EVAL_MODEL
Expand Down