can1357 01b5a2ec26 feat(coding-agent/tool-discovery): improved tool discovery tokenization and scoring ...

- Normalized tool discovery token parsing with Unicode decomposition, removing combining marks and splitting acronym and camel-case boundaries for better tokenization.
- Expanded token separators to treat any non-letter or non-digit character as a boundary during indexing.
- Added a BM25_DELTA term to the BM25 scoring calculation to adjust relevance scoring for matching terms.

2026-05-11 00:53:50 +02:00

..

tool-index.ts

feat(coding-agent/tool-discovery): improved tool discovery tokenization and scoring

2026-05-11 00:53:50 +02:00