6387872051
ADR-0073c shipped he_chesed_v1, he_shalom_v1, he_tzedek_v1 with lossy EN-collapse alignment edges (he-021 → en-collapse-love @ 0.63, etc.) but the synthetic en-collapse-* targets didn't exist in any mounted lexicon. Result: the three lenses ratified but stayed dormant — the runtime OOV gate fired on "What is love?" / "What is peace?" / "What is justice?" before the lens engagement path got a chance. This commit adds a minimal pack whose lexicon carries exactly those three synthetic anchors: en-collapse-love lemma="love" domain=collapse_anchor.love en-collapse-peace lemma="peace" domain=collapse_anchor.peace en-collapse-justice lemma="justice" domain=collapse_anchor.justice Mounted last in DEFAULT_RESOLVABLE_PACK_IDS — cognition / relations packs win first-match on any future collision. No real content pack currently carries these lemmas (grep-confirmed) so the mount adds no collision risk. The pack-grounded surface for "What is love?" advertises its nature honestly via the pack id (en_collapse_anchors_v1) and the domain string (collapse_anchor.love) — the surface is intentionally minimal; the substantive content arrives via the lens annotation [lens(he_chesed_v1):covenant-love] / [lens(he_shalom_v1):wholeness-peace] / [lens(he_tzedek_v1):right-order]. chat/pack_grounding.py:_en_lemma_to_entry_id() now reads both en_core_cognition_v1 and en_collapse_anchors_v1, with cognition winning on lemma collision. New test file tests/test_en_collapse_anchors_v1_pack.py pins: - each anchor lemma resolves to its synthetic entry_id - collapse pack mounted last (precedence guarantee) - each of the three lenses engages on its target English prompt - baseline surface (no lens) still advertises anchor nature Validation: - Cognition eval byte-identical (100/100/91.7/100) - 160 lens/pack/resolver tests pass + 8 new - anchor-lens-tour green - register-tour green |
||
|---|---|---|
| .. | ||
| data | ||
| __init__.py | ||
| __main__.py | ||
| compiler.py | ||
| en_seeder.py | ||
| evidence.py | ||
| schema.py | ||