test: Add evaluation for BigQuery tools

We should treat this as the first step towards building a robust eval story for BQ tools.

PiperOrigin-RevId: 807247053
This commit is contained in:
Google Team Member
2025-09-15 08:16:33 -07:00
committed by Copybara-Service
parent 7870480c63
commit 103e88e95f
5 changed files with 701 additions and 0 deletions
@@ -0,0 +1,6 @@
{
"criteria": {
"tool_trajectory_avg_score": 0.7,
"response_match_score": 0.7
}
}