45 lines
1.5 KiB
TOML
45 lines
1.5 KiB
TOML
version = "1.0"
|
|
|
|
[metadata]
|
|
author = "worker"
|
|
repo = "potion-app"
|
|
commit = "f89abccf"
|
|
# The toolkit release this task was created with. Written by the toolkit —
|
|
# leave it in place: task tooling reads it to know which toolkit's assets
|
|
# this task grades with.
|
|
toolkit_version = "037cfcf94b"
|
|
# Set true for a task about a UI: the trial gets Playwright + Chromium (`pw <script.js>`),
|
|
# and on claude the `Read` tool so the agent can view a screenshot it takes. Leave false
|
|
# when the point of the task is that something cannot be verified.
|
|
browser = false
|
|
|
|
[verifier]
|
|
# The verifier runs the repo's test suite and then the grader, which can take a
|
|
# while; 7200s (2 hours) gives headroom. Large suites may need more.
|
|
timeout_sec = 7200.0
|
|
|
|
[agent]
|
|
# The coding-agent harness this task is written for — the one you used while
|
|
# authoring it. Trials run this harness; leave it as codex unless you
|
|
# authored against another. Keep it INSIDE this table: a second [agent] table is
|
|
# invalid TOML and makes the whole file unreadable.
|
|
# See your options with: python3 scripts/resolve_harness.py --list
|
|
harness = "codex"
|
|
timeout_sec = 18000.0
|
|
|
|
[environment]
|
|
build_timeout_sec = 6000.0
|
|
cpus = 2
|
|
memory_mb = 4096
|
|
storage_mb = 10240
|
|
gpus = 0
|
|
# Leave this true, and don't add network_mode or allowed_hosts: the grader reaches the
|
|
# model API over the network, so restricting egress here makes every trial ungradable.
|
|
allow_internet = true
|
|
|
|
[verifier.env]
|
|
ANTHROPIC_API_KEY = "${ANTHROPIC_API_KEY}"
|
|
ANTHROPIC_BASE_URL = "${ANTHROPIC_BASE_URL}"
|
|
|
|
[solution.env]
|