Project-2 baseline

This commit is contained in:
2026-10-04 21:19:23 -04:00
parent 0f04889edf
commit 213eb3c403
861 changed files with 1710 additions and 3363322 deletions

View File

@@ -7,7 +7,7 @@ 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"
toolkit_version = "1.0.0"
# 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.
@@ -38,6 +38,7 @@ gpus = 0
allow_internet = true
[verifier.env]
GRADER_HARNESS = "codex"
ANTHROPIC_API_KEY = "${ANTHROPIC_API_KEY}"
ANTHROPIC_BASE_URL = "${ANTHROPIC_BASE_URL}"