wip: run tb2 and fix modal instantiation

This commit is contained in:
alt-glitch 2026-04-01 16:55:03 -07:00
parent 3baafea380
commit 3befb9389f
7 changed files with 90 additions and 23 deletions

View file

@ -32,8 +32,8 @@ export PYTHONUNBUFFERED=1
# These go to the log file; tqdm + [START]/[PASS]/[FAIL] go to terminal
export LOGLEVEL=INFO
python terminalbench2_env.py evaluate \
--config default.yaml \
uv run python environments/benchmarks/terminalbench_2/terminalbench2_env.py evaluate \
--config environments/benchmarks/terminalbench_2/default.yaml \
"$@" \
2>&1 | tee "$LOG_FILE"