Shivam 4e95d4c71f feat(echo-trap): add tokenizer-aware repetition scoring (#242) ... Closes #241. Adds opt-in tokenizer-aware n-gram path for the v0.70.0 Part F echo-trap detector. The existing whitespace `score_echo_signal` is unchanged; callers opt in via the new `score_trajectory_repetition_tokenized` / `score_echo_signal_tokenized` helpers or the `--echo-trap-tokenizer-aware` train flag. Acceptance criterion from #241 verified: synthetic case where decoded strings differ by punctuation but token-id sequence repeats — whitespace path returns OK, tokenizer-aware path returns TRAP.		2026-05-25 19:46:51 +05:00
..
__init__.py	Initial project setup: CLI skeleton + config + trainer + data pipeline	2026-02-20 16:14:56 +05:00
loader.py	fix: v0.21.1 — Windows UnicodeEncodeError, load_config str, recipe count	2026-04-02 14:31:17 +05:00
schema.py	feat(echo-trap): add tokenizer-aware repetition scoring (#242)	2026-05-25 19:46:51 +05:00