pj bcce9d9e90 Calibration artifact: the checks and the raw commands side by side ...

The pilot is only worth something if the checks agree with a person reading the
transcript. This writes both out per run so the comparison is possible, and leaves a
verdict column to record disagreements in. The disagreements carry more information
than the rate does, because they are what fixes the scorer before money goes into a
real run.

Claude-Session: https://claude.ai/code/session_01Cq98H7sNoSJdL3W98f18bu

2026-08-31 21:44:04 +05:30

..

baseline.py

Scratch directory task, event adapter, per-run checks

2026-08-31 21:36:13 +05:30

calibrate.py

Calibration artifact: the checks and the raw commands side by side

2026-08-31 21:44:04 +05:30

model_check.py

Scratch directory task, event adapter, per-run checks

2026-08-31 21:36:13 +05:30

pilot.py

Analysis rows, pilot and report scripts

2026-08-31 21:38:52 +05:30

report.py

Analysis rows, pilot and report scripts

2026-08-31 21:38:52 +05:30

smoke_mock.py

Repo skeleton, pinned environment, free smoke test

2026-08-31 21:14:58 +05:30

smoke_scratch.py

Scratch directory task, event adapter, per-run checks

2026-08-31 21:36:13 +05:30

verify_snapshot.py

Do not attribute the harness's own filesystem actions to the agent

2026-08-31 21:43:22 +05:30