version = "1.0" [metadata] author = "worker" repo = "stocks-in-the-future" commit = "63732df2" # Set true for a task about a UI: the trial gets Playwright + Chromium (`pw `), # 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 claude-code 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 = "claude-code" timeout_sec = 18000.0 [environment] build_timeout_sec = 6000.0 cpus = 2 memory_mb = 4096 storage_mb = 10240 gpus = 0 allow_internet = true [verifier.env] ANTHROPIC_API_KEY = "${ANTHROPIC_API_KEY}" ANTHROPIC_BASE_URL = "${ANTHROPIC_BASE_URL}" [solution.env]