feat(trainer): policy-optimization objective MENU (ADR-014)

fix(phase-8): close all 5 cross-family final-verify findings + regression tests

feat(wave-a): close ADR-011 (SDPO alignment indices) + ADR-012 (review findings)

review+fix: cross-family adversarial ADR review (owed item) + remediation

feat(trainer): ADR-008 Dr.GRPO config + SDPO strict-alignment guard

Wave 21b: skip zero-signal SDPO on empty-recovery error turns + real-trace validation

Wave 21: close both Wave 20 debt items — chat-template alignment + structural is_error

Wave 19: production-grade SDPO via ComposerDataCollator + adapter + collator fixes

Wave 15: 4-angle multi-model self-critique caught 2 math BLOCKERs in primary loss kernels; fixed against upstream byte-for-byte + GSM8K example + ergonomics

Wave 10 — packaging: composer_replication is now pip-installable