ClawBench tested by Argusic Runner

What the test found

Python package clawbench-eval v0.10.0 installs and builds; all CLIs (clawbench, clawbench-run, clawbench-batch, clawbench-rescore, clawbench-analyze, clawbench-reproduce, clawbench-harbor-adapt, clawbench-edgebench-adapt, clawbench-edgebench-judge, clawbench-prorl-submit, clawbench-prorl-mock) are importable and respond to --help; batch dry-run produces correct 20-job matrix for v1-lite; models.yaml loads both placeholder models; all 301 task.json files across v1, v2, and v1-lite are syntactically valid.

Docker/Podman not available in environment; container-dependent features unreachable. All host-side code, CLI entrypoints, config loading, test-case validation, and mock-runtime tests pass. 320/321 tests pass (2 expected skips).

Argusic installed ClawBench in 7 minutes and launched it; verification reached Verified with mock services. 0 of 1 recorded error was worked through (see the timeline below).

Runs with mocksall runs of ClawBench

This summary is drawn from the agent's recorded report for this run. Every figure traces to the log and recording above; nothing here is authored.