Drew T 41b259e528 fix(wave): cards keyed by (binary,fn) — t5a received 48/48 ANOTHER binary's card (R48); t5_cards.py builds the target's OWN fuel (tu_ref 88% / decl_prior 98%) via wave_card_fuel.py extracted from build_wave_atlas (R33); t5_bank.sh recovers un-banked drafts via fix_tu_ret_decls (2/2 on t5a); distill workflow generalized (P31 S63 T5)

2026-08-26 20:19:41 -06:00

..

ab_match.js

feat(phase-22): cheap-tier A/B experiment harness + findings

2026-06-29 12:52:39 -06:00

claude_wave_distill.js

fix(wave): cards keyed by (binary,fn) — t5a received 48/48 ANOTHER binary's card (R48); t5_cards.py builds the target's OWN fuel (tu_ref 88% / decl_prior 98%) via wave_card_fuel.py extracted from build_wave_atlas (R33); t5_bank.sh recovers un-banked drafts via fix_tu_ret_decls (2/2 on t5a); distill workflow generalized (P31 S63 T5)

2026-08-26 20:19:41 -06:00

claude_wave_draft.js

feat(tools): T5 wave draw/bank halves — t5_targets.py (routed, ledgered, band-stratified draw) + t5_bank.sh (judge → R22 sweep → commit); claude_wave_draft.js generalized; packs/judge refuse duplicate fn names (R43/R48); sweep #8 213/213 (P31 S63 T5.1)

2026-08-26 19:35:54 -06:00

distill.js

feat(phase-21): R2/R3 — the learning flywheel (class-grouped waves + distill)

2026-06-21 13:56:59 -06:00

family_core_wave.js

feat(phase-29): SESSION-21 T1-T3 — the frontier measured, the family-exemplar wave, 3 tool fixes

2026-07-26 23:37:35 -06:00

t5_scaleup.js

feat(phase-25): T5b batch-1 (partial) — +1877 fns (fleet 71.47->72.02%)

2026-07-08 22:56:01 -06:00

wave_binary.js

fix(workflow): wave_binary drafters MUST copy the winner back to draftDir/<fn>.c (a wave's 24 winners were written under scratch names and recovered only from agent transcripts)

2026-07-23 22:38:10 -06:00

worker_wave.js

feat(phase-29 T3): the §53 has_mid_jr INTERLOCK + worker_wave -O0 build-step fix

2026-07-17 02:12:17 -06:00