# tera-crow-nav — fly a crow to a waypoint on sixteen replies.
# See environments/tera_spatial for what it measures and where these two integers
# came from (`measure_hold.py`, not judgement).
#
#   uv run --project environments/tera_spatial eval @ configs/tera_crow_nav.toml \
#     --model brain-qwen38-dspark \
#     --client.base-url http://100.127.247.67:8001/v1 \
#     --client.api-key-var SPARK_API_KEY --no-push --no-rich -c 8
#
# `node` >= 22.18 must be on PATH: the environment is TypeScript and is executed,
# not translated.
num_tasks = 16
num_rollouts = 2

[env.taskset]
id = "tera-crow-nav"
num_tasks = 16
max_turns = 16    # replies. Sixteen is where the ceiling first becomes reachable.
max_hold = 12     # steps one reply is held for. 16 x 12 = 192 against a 300-step cap,
                  # so what binds is the turn budget and never the simulator's own.
default_hold = 6  # what an unreadable reply costs. Never zero.
seed_base = 115

[env.agent.harness]
id = "null"    # one completion per turn, no tools; the env programs the loop

[env.agent.runtime]
# ⚠️ REQUIRED since verifiers 0.3.1.dev59, 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"