Kevin Hu
Kevin Hu
@liuzhuosin What about this PR #11649 ?
During increamental synchronization, it's not easy to delete removed files. We're working on it.
What about disabling `Reasonning`? 
It seems no searching procedure was triggered which was controled by LLM. Try another LLM.
What about Deepseek-V3?
For DDL text files, set `;` as delimiter and leave the chunk token number as default. File number should not be concerned.
Split via delimiter firstly, then, merge those pieces by `chunk token number`.
Where did you get the original DSL from?
Appreciations! Please submit the corresponding `uv.lock` as the `pyproject.yaml` was changed.
Please resolve the conflicts.