Jack f41f866aa1 Fix(parser): keep real line breaks when merging HTML fragments and PDF boxes (#17856) ...

Net effect: inline prose stays on one line (`Hello World`), real `<br>` boundaries survive (including before tags and repeated breaks), and source formatting whitespace no longer over-splits.

2026-08-06 09:57:23 +08:00

..

admin

fix(admin,api): honor STORAGE_IMPL when surfacing file_store backend (closes #17294) (#17441)

2026-07-29 11:13:20 +08:00

agent

feat(agent): add Querit search tool (#17548)

2026-07-30 09:36:16 +08:00

api

Fix: display embedding model name in list dataset api response (#17832)

2026-08-05 14:51:07 +08:00

common

fix(common/misc_utils): allow once decorator retries after failure (#16174)

2026-07-31 22:43:18 +08:00

data_source

feat: make blob storage size threshold configurable (#16806)

2026-07-10 21:36:12 +08:00

deepdoc

Fix(parser): keep real line breaks when merging HTML fragments and PDF boxes (#17856)

2026-08-06 09:57:23 +08:00

llm

feat: add Mistral OCR (/v1/ocr) as a document parser; fix "Can't find model" mis-tag (#5782, #7075) (#17057)

2026-07-24 21:07:48 +08:00

mcp

Fix: MCP document metadata cache can loop forever when documents returns an empty docs page (#16285)

2026-06-24 13:09:48 +08:00

memory/utils

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

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

rag

Revert "feat: Go knowledge compiler with scheduler-driven dataset compilation" (#17897)

2026-08-05 21:50:28 +08:00

test_testcases

fix: test drift on go specific proxy scheme (#16796)

2026-07-13 16:41:38 +08:00

tools

fix lefthook (#17023)

2026-07-17 11:18:10 +08:00

conftest.py

feat(agent): align Go agent behavior with Python (except retrieval component) (#16225)

2026-06-22 11:58:29 +08:00

test_test_chunk_feedback_package.py

…