# drop-table-inference — the estimate is graded on the kills the model never saw.
#
#   uv run eval @ configs/drop_table_inference.toml --model <model-id>
num_tasks = 16
num_rollouts = 2

[env.taskset]
id = "drop-table-inference"
visible_kills = 1200     # kills the model reads, as a tally
held_out_kills = 40000   # kills it is scored on

[env.agent.harness]
id = "null"    # pure-trace reward: one completion, no tools, no runtime

[env.agent.runtime]
# ⚠️ REQUIRED since verifiers 0.3.1, which changed the default agent runtime from
# `subprocess` to `prime` — a REMOTE sandbox. Without this the run exits
# `SystemExit: not authenticated with prime` before a single rollout, having already created
# its output directory and a zero-line traces.jsonl, so it reads as a failed eval rather than
# an unauthenticated one. Nothing here needs a sandbox: the reward is a pure function of the
# trace and the harness is `null`.
type = "subprocess"