24 lines
976 B
TOML
24 lines
976 B
TOML
# grand-exchange — see environments/grand_exchange for what it measures.
|
|
#
|
|
# uv run eval @ configs/grand_exchange.toml --model <model-id>
|
|
num_tasks = 16
|
|
num_rollouts = 2
|
|
|
|
[env.taskset]
|
|
id = "grand-exchange"
|
|
num_items = 5 # items in the basket, one per price tier
|
|
visible = 56 # ticks the model reads
|
|
held_out = 30 # ticks its orders are executed against
|
|
|
|
[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"
|