jekalmin/extended_openai_conversation 3.0.0-beta4

on GitHub

What's Changed

• Fix composite function consuming unnecessary contexts by @jekalmin in #388
• Expose error message in conversation by @jekalmin in #389
• Change default settings to suit reasoning model by @jekalmin in #390
  • model: gpt-4o-mini → gpt-5-mini

    Model	Input	Cached input	Output
    gpt-4o-mini	$0.15	$0.075	$0.60
    gpt-5-mini (flex)	$0.125	$0.0125	$1.00

  • max tokens: 150 → 500
  • max function calls per conversation: 1 → 3
  • prompt
  • functions
    • Add delay properties in execute_services function.
    • Add get_attributes function
  • service tier: flex
  • reasoning effort: low

Full Changelog: 3.0.0-beta3...3.0.0-beta4