goose vs Harness²

goose

Telemetry off until the user opts in, with the collected fields listed. Autonomous mode, which approves every tool call, is the default.

Harness²

Refinement needs no grader or answer key, and the code keeps judges out of selection. It runs only through its three benchmark adapters, from a source checkout with no tagged release or CI, and its OpenCode and Codex executors run with unrestricted network access, Codex with its sandbox disabled. The benchmark gains are the authors' claims.

goose

1. Set GOOSE_MODE=smart_approve or approve before a run. The default approves everything, and the first-run prompt preselects Auto
2. Pass --max-turns with a real limit. The default is 1000
3. Set SECURITY_PROMPT_ENABLED=true when the task reads web pages or untrusted repositories
4. Use --output-format json and --no-session in CI, and check the exit code
5. Point remotes and links at aaif-goose/goose and goose-docs.ai. The block/goose paths redirect

Harness²

1. Don't plan to call Harness² as a service. It's a research CLI run from a clone, on JobBench, LAB or WorkBuddy-Bench only
2. Ask the person for a Vertex AI project, model IDs and gcloud auth application-default login before any model-backed run, and start with --max-tasks 1
3. Run executors behind an egress firewall and block huggingface.co and github.com after setup, as the docs advise, so rubrics can't be fetched
4. Write .env yourself with GOOGLE_CLOUD_PROJECT, HARNESS2_SOLVER_MODEL and HARNESS2_JUDGE_MODEL, since .env.example isn't shipped, and never commit it
5. Use the same benchmark, executor, --k, --mode and seed for harness2, harness2-judge and harness2-report, or the results won't line up