MarMar Labs cd27ae4c6e fix(memory): put the keyword weight in the text slot of the fusion expression (#18989) ...

Fix memory search hybrid weights inverted (slot 1 is vector weight, not keyword). Now matches build_fusion_expr. At 0.7, memory search becomes keyword-dominant (was vector-dominant).

2026-09-01 16:14:36 +08:00

..

test_memory_message_service.py

fix(memory): put the keyword weight in the text slot of the fusion expression (#18989)

2026-09-01 16:14:36 +08:00

test_memory_message_timestamp_normalization.py

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

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

test_tenant_model_service_max_tokens.py

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

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