Is your feature request related to a problem? Please describe:
Users often complain about wasting tokens when asking questions about code, even though they don't need code changes.
Describe the solution you'd like:
Add a toggle near the text box where users enter prompts in Bolt. When enabled, this toggle should utilize an alternative LLM specifically for answering questions about code, prioritizing cost-effectiveness and accuracy. This feature would override normal behavior when asking questions, preventing token waste by not using Claude 3.5 Sonnet.
Describe alternatives you've considered:
One possible solution could be to provide a separate "question-answering" mode in Bolt's settings, which would switch to the alternative LLM and disable code generation for prompts. However, this might add complexity to the app's UI and make it harder for users to find the right mode.
Additional context:
This complaint has been mentioned by multiple users in the Discord server, indicating a need for a more efficient solution. This should help with the concern users have with "wasting tokens".
Is your feature request related to a problem? Please describe:
Users often complain about wasting tokens when asking questions about code, even though they don't need code changes.
Describe the solution you'd like:
Add a toggle near the text box where users enter prompts in Bolt. When enabled, this toggle should utilize an alternative LLM specifically for answering questions about code, prioritizing cost-effectiveness and accuracy. This feature would override normal behavior when asking questions, preventing token waste by not using Claude 3.5 Sonnet.
Describe alternatives you've considered:
One possible solution could be to provide a separate "question-answering" mode in Bolt's settings, which would switch to the alternative LLM and disable code generation for prompts. However, this might add complexity to the app's UI and make it harder for users to find the right mode.
Additional context:
This complaint has been mentioned by multiple users in the Discord server, indicating a need for a more efficient solution. This should help with the concern users have with "wasting tokens".