Fixed version of the broken dynamo/log-report task.
- Format -
task.tomlsetartifacts = "/app/out.json": a string where Harbor's schema wants a list, pointing at a file the task never produces. - Environment - the Dockerfile used the floating tag
python:latest, and it copiedsolution_hint.py(a full reference solution) into the agent image. - Verifier - only checked that
report.jsonexisted and was non-empty, soecho '{}'scored 1.0. It also wrote the reward to/app/reward.txtinstead of/logs/verifier/reward.txt, and never emittedctrf.json. - Instruction - never named the output path, the filename, the JSON keys, or any success criteria.
artifacts = ["/app/report.json"], matching what the task actually writes.- Base image pinned by digest,
solution_hint.pydeleted from the build context. - Verifier parses the JSON and asserts the real values (6, 3,
/index.html), writes reward to/logs/verifier/reward.txtand CTRF to/logs/verifier/ctrf.json. instruction.mdrewritten with four numbered success criteria, mapped one-to-one onto four tests.
harbor run -p log-report --agent oracle # reward 1.0
harbor run -p log-report --agent nop # reward 0.0