deer-flow

mirror of https://github.com/bytedance/deer-flow.git synced 2026-07-28 08:56:13 +00:00

History

feat(memory): built-in FTS5/BM25 retrieval adapter (#4360 )

* feat(memory): integrate FTS5 retrieval adapter

* deps: add jieba as default dependency for Chinese tokenization

Without jieba, FTS5 unicode61 tokenizer treats entire Chinese sentences
as single tokens, making single-character or sub-phrase searches
impossible (e.g. '吃' or '油泼面' returns 0 hits against
'用户喜欢吃油泼面'). jieba segments Chinese text into meaningful tokens
before indexing.

* fix(memory): avoid treating hyphens as FTS5 operators

* feat(memory): make Chinese tokenization optional

* fix(memory): warm every requested retrieval scope

* fix(memory): close retrieval resources on shutdown

* fix(memory): close backend when shutdown flush fails

* fix(memory): recreate corrupt retrieval index

* fix(memory): tolerate partial retrieval rebuilds

* fix(memory): warm retrieval index in background

* fix(memory): preserve shutdown flush budget

* fix(memory): stop retrying partial lazy rebuilds

* fix(memory): close retrieval through storage

* refactor(memory): simplify retrieval scope limit

* docs(memory): clarify retrieval shutdown lifecycle

---------

Co-authored-by: Willem Jiang <willem.jiang@gmail.com>

2026-07-27 23:17:18 +08:00

lead_agent

bench(checkpoint): production-shaped full/delta benchmark with configurable snapshot frequency (#4467 )

2026-07-27 11:47:49 +08:00

memory

feat(memory): built-in FTS5/BM25 retrieval adapter (#4360 )

2026-07-27 23:17:18 +08:00

middlewares

feat(clarification): structured form fields for human-input cards (#4400 Phase 1) (#4406 )

2026-07-27 14:05:31 +08:00

__init__.py

feat(checkpoint): dual-mode checkpoint storage with LangGraph DeltaChannel (#4292 )