For the complete documentation index, see llms.txt. This page is also available as Markdown.
Backend Configurations
1
tokenConsumptionLimit
This key sets the total token allowance for the AI service. The backend will use this value as the maximum total tokens that can be consumed.
2
tokenConsumptionTrigger
This key sets a percentage of the tokenConsumptionLimit. When consumption reaches or exceeds this percentage, a trigger flag will be set to true in the API response.
