天海蒼灆 e9cace9a09 fix: preserve non-string values in update_metadata_to (#17346) ...

## Summary
- Broaden `update_metadata_to` to keep `bool` / `int` / `float` / `None`
and structured values (e.g. PDF `outline` list[dict]) while retaining
string / list[str] merge+dedupe for LLM metadata.
- Fixes document system fields (`_isCurrent`, `_version`,
`_processStatus`) being dropped when parse persists PDF outline via full
`meta_fields` replace.

---------

Co-authored-by: Cursor <cursoragent@cursor.com>

2026-08-21 17:53:27 +08:00

..

data_source

Feat: data source test connection with unified connector validation (#14992)

2026-08-18 09:36:48 +08:00

doc_store

fix(doc_store): retry transient connection errors in pool init (#17196)

2026-08-21 13:56:06 +08:00

__init__.py

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

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

aimlapi_utils.py

fix(aimlapi): send attribution headers on every aimlapi.com request (#17491)

2026-07-28 23:22:27 +08:00

asyncio_utils.py

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

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

config_utils.py

feat: Gaussdb adaptation (#17703)

2026-08-18 09:53:11 +08:00

connection_utils.py

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

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

constants.py

Feat: Compilation benefit naive rag. (#17555)

2026-07-30 18:39:01 +08:00

crypto_utils.py

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

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

decorator.py

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

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

exceptions.py

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

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

file_utils.py

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

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

float_utils.py

Fix: overlap cannot be properly applied (#12828)

2026-01-27 12:43:01 +08:00

http_client.py

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

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

llm_request_context.py

fix(task_executor): fix Langfuse flush/shutdown deadlock that freezes document parsing (#16502)

2026-07-07 19:06:30 +08:00

log_utils.py

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

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

mcp_tool_call_conn.py

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

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

metadata_es_filter.py

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

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

metadata_gaussdb_filter.py

feat: Gaussdb adaptation (#17703)

2026-08-18 09:53:11 +08:00

metadata_infinity_filter.py

fix(metadata): Infinity push-down must reject multi-valued-unsafe negative ops (≠, not in) (#16943)

2026-07-18 18:47:25 +08:00

metadata_utils.py

fix: preserve non-string values in update_metadata_to (#17346)

2026-08-21 17:53:27 +08:00

misc_utils.py

fix: avoid quadratic dedup in RAG merge paths (#18135)

2026-08-20 11:50:27 +08:00

parser_config_utils.py

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

query_base.py

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

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

settings.py

feat: Gaussdb adaptation (#17703)

2026-08-18 09:53:11 +08:00

signal_utils.py

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

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

ssrf_guard.py

Fix: allow any host for url for development (#16459)

2026-06-30 10:19:04 +08:00

string_utils.py

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

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

tag_feature_utils.py

Fix Tag weight should be greater than 0 (#16657)

2026-07-06 16:06:27 +08:00

text_utils.py

Feature rtl support (#13118)

2026-03-02 13:03:44 +08:00

time_utils.py

fix(memory): normalize invalid extraction timestamps (#18463)

2026-08-19 18:31:51 +08:00

token_utils.py

feat(agent): report accurate aggregated token usage and propagate session/user + input/output to Langfuse for agent runs (#16420)

2026-07-02 09:35:28 +08:00

versions.py

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

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