eda1628ec3
A solver-agnostic harness that grades coding-agent task success with an executable test oracle (tests fail before, pass after; pristine test files restored to prevent gaming) and pairs it with measured energy (jouleclaw IOReport, idle-subtracted, sub-window readings flagged unreliable), vendor-billed dollars, and token-estimated cloud energy. Solvers: reference, noop, claude, gemini, and cascade (the real joule_core engine via joule-coded). --passes shows L0 cache amortization. Headline (RESULTS.md): on a realistic operation mix, the cascade and frontier claude both resolve 100%, but the cascade costs ~10x less per task -- mechanical ops close locally at L1 for free, novel ops escalate to the same model once, and repeats are free from the L0 cache. Co-Authored-By: Claude Opus 4.8 (1M context) <[email protected]>
5 lines
138 B
TOML
5 lines
138 B
TOML
name = "greeting"
|
|
prompt = "replace Helo with Hello"
|
|
test_cmd = "python3 -m pytest -q"
|
|
test_files = ["test_greet.py"]
|
|
target = "greet.py"
|