bug: Thread assistant - Switching model, and input assistant, the selected model auto revert back to previous used model with setting mismatch

[Van-QA]

Describe the bug Switching model from GPT to Hub model (or vice versa) and input assistant, the selected model auto revert back to previous used model with setting mismatch.

Steps to reproduce Steps to reproduce the behavior:

1. Create new thread using any model
2. Send message
3. Switch the model to GPT => the inference setting should be gone
4. Input assistant value => the inference setting is gone, but the model was switched back to the model selected in step 1

Expected behavior At step 4, if the model reverted back to the most recent used model (that users last sent message), the setting should follow up accordingly

Screenshots

Environment details

• Operating System: MacOS
• Jan Version: 0.4.3
• Processor: Apple M2 Pro
• RAM: 16GB

Logs If the cause of the error is not clear, kindly provide your usage logs:

• tail -n 50 ~/jan/logs/app.log if you are using the UI
• tail -n 50 ~/jan/logs/server.log if you are using the local api server Making sure to redact any private information.

Additional context