Jack ebd6be09c7 feat(title-chunker): configurable token-count cap with sentence-boundary re-split (#18455) ...

## Summary

The TitleChunker (both `hierarchy` and `group` methods) had no
token-size ceiling, so a long section without sub-headings became one
giant chunk. This adds a configurable `chunk_token_cap` that guarantees
every text chunk stays within a token budget.

2026-08-18 21:03:51 +08:00

..

chunker

feat(title-chunker): configurable token-count cap with sentence-boundary re-split (#18455)

2026-08-18 21:03:51 +08:00

compiler

Search in navigation tree & store graph content in nav_doc (#18303)

2026-08-14 22:26:57 +08:00

extractor

Feat: add wiki folder (#16749)

2026-07-08 20:08:14 +08:00

parser

fix(tests): isolate token chunker imports (#18018)

2026-08-13 15:43:11 +08:00

tests

feat(title-chunker): configurable token-count cap with sentence-boundary re-split (#18455)

2026-08-18 21:03:51 +08:00

tokenizer

refa: resolve tenant model refs consistently (#16744)

2026-07-09 14:02:08 +08:00

__init__.py

Feat: refine dataflow and initialize dataflow app (#9952)

2025-09-05 18:50:46 +08:00

base.py

Refactor: reformat all code for lefthook using ruff and gofmt (#16585)

2026-07-03 12:53:39 +08:00

file.py

Refactor: reformat all code for lefthook using ruff and gofmt (#16585)

2026-07-03 12:53:39 +08:00

pipeline.py

fix: optimize dataflow indexing and logs (#17737)

2026-08-03 19:15:44 +08:00