Qin Haojie 38c324bc97 fix(security): clean up code scanning and runtime findings (#1596) ...

* fix(security): clean up code scanning and runtime findings

Harden path and logging boundaries, remove noisy cleanup issues,
and keep observability failures from breaking runtime flows.

* fix(security): close werewolf and feishu validation gaps

Block the remaining path traversal bypass in the werewolf demo,
and validate Feishu hosts on the main parse() entry point.

2026-04-21 10:06:46 +08:00

..

__init__.py

Feat(benchmark): Add benchmark/RAG : RAG system evaluation framework (#825)

2026-04-01 14:39:53 +08:00

download_dataset.py

fix(security): clean up code scanning and runtime findings (#1596)

2026-04-21 10:06:46 +08:00

prepare_dataset.py

Feat(benchmark): Add benchmark/RAG : RAG system evaluation framework (#825)

2026-04-01 14:39:53 +08:00

run_sampling.py

Feat(benchmark): Add benchmark/RAG : RAG system evaluation framework (#825)

2026-04-01 14:39:53 +08:00

sample_dataset.py

Feat(benchmark): Add benchmark/RAG : RAG system evaluation framework (#825)

2026-04-01 14:39:53 +08:00