Can logs be split during parallel query execution?

Please describe your suggestion in English.

Is your feature request related to a problem? Please describe. When deploying deep-searcher using the Deployment method (main.py), the chain of thought logs for multiple parallel queries are mixed together. Is it possible to separate the chain of thought logs for each parallel query to facilitate subsequent analysis and debugging?

Describe the solution you'd like

1. Generate a unique ID for each query and record it in the log for subsequent analysis and debugging.
2. Use different log files or log streams to store the thought chain logs for each query to avoid mixing.

Describe alternatives you've considered None

Additional context None