pj 5f1f50c2fb fix(campaign): the action count leaves the setup's login out on a model run ...

Defects per thousand actions divided by every dispatched step, so a
spec whose setup logs in inflated the denominator by however many steps
that took. It is the same error the run gate had, and it does not cancel
between arms.

A model run is separable because only an llm-selected action stamps
next_action.source. A seeded run is not: its setup returns through the
same entry with no marker, and 11261 dispatched steps across the 169
recorded runs carry no source at all, so excluding on it blind would
report every seeded run as having explored nothing. The seeded arm
counts as before and a test pins that.

2026-08-18 16:52:22 +05:30

..

internal-tools

fix(campaign): the action count leaves the setup's login out on a model run

2026-08-18 16:52:22 +05:30

sanderling

feat(cli): --allow-no-properties opts a run out of the refusal

2026-08-17 23:27:25 +05:30