Skip to content

pxx 2.4.3

Choose a tag to compare

@github-actions github-actions released this 17 Aug 02:17
· 17 commits to v2 since this release
9eabc7a

Fixed

  • Reviewer/judge now decodes greedily (temperature: 0) — the review gate is reproducible.
    The model-backed reviewer's request omitted temperature, so against an Ollama endpoint the
    server default (0.8) made the judge nondeterministic: the same diff produced different
    verdicts run-to-run, and pxx calibrate swung across its MIN_AGREEMENT / MIN_RECALL
    thresholds — so a calibrated reviewer couldn't be trusted to stay calibrated, and a single
    calibration near a threshold was a coin-flip. pxx/review.py now sends temperature: 0, pinning
    the judge to greedy decoding. Surfaced by a reachable → unparseable → calibrate → replace
    reviewer diagnostic that exposed the swing. Test asserts the reviewer payload carries
    temperature == 0.