Determine chunk size based on model being used

[Pwuts]

See:

• Improve chunking and chunk handling #38

• Maximum context length exceeded after browse_website #796

• Prompt overflows aren't handled gracefully #1841

• Settings:

  • BROWSE_CHUNK_MAX_LENGTH
  • FAST_TOKEN_LIMIT SMART_TOKEN_LIMIT

The token limit depends directly on the LLM being used, so these settings should be consolidated and calculated where possible, instead of letting the user set them by hand.

[ntindle]

Would love a prompts info utils with all this info in it

[github-actions]

This issue has automatically been marked as stale because it has not had any activity in the last 50 days. You can unstale it by commenting or removing the label. Otherwise, this issue will be closed in 10 days.

[github-actions]

This issue was closed automatically because it has been stale for 10 days with no activity.