Back to Registry
tau2.retail.refund_processed
HARD
Queries mock/real retail API to confirm a refund has been processed with the expected amount and status. Catches agents that claim refunds were issued but the actual state shows otherwise.
Scorecard
| Determinism | deterministic |
| Evidence Quality | api-state |
| Intended Use | eval-and-train |
| Gating Required | No |
| Permissions | net:http |
Test Fixtures
9 total
| Type | Count |
|---|---|
| Positive | 3 |
| Negative | 3 |
| Adversarial | 3 |
Metadata
| Version | 0.1.0 |
| Domain | retail |
| Task Type | refund_verification |
| Contributor | vr.dev |
| Source | arXiv:2406.12045 |
Use in SDK
# CLI
vr verify --verifier tau2.retail.refund_processed --ground-truth '{"order_id": "ORD-42"}'
# Python
from vrdev import verify
result = verify("tau2.retail.refund_processed", ground_truth={"order_id": "ORD-42"})
# API
curl -X POST https://api.vr.dev/v1/verify \
-H "X-API-Key: vr_live_..." \
-d '{"verifier": "tau2.retail.refund_processed", "ground_truth": {"order_id": "ORD-42"}}'