bolt.new/app/lib/.server/llm/constants.ts

// see https://docs.anthropic.com/en/docs/about-claude/models
export const MAX_TOKENS = 8000;

// limits the number of model responses that can be returned in a single request
export const MAX_RESPONSE_SEGMENTS = 2;
feat: add first version of workbench, increase token limit, improve system prompt 2024-07-17 18:54:46 +00:00			`// see https://docs.anthropic.com/en/docs/about-claude/models`
Update max_tokens in constants.ts max_tokens for llama 3.1 models must be less than or equal to 8000 but it is set to 8192. just change it to 8000 and the error is fixed. 2024-10-21 14:02:57 +00:00			`export const MAX_TOKENS = 8000;`
feat: add support for message continuation (#1) 2024-07-19 09:12:55 +00:00
			`// limits the number of model responses that can be returned in a single request`
			`export const MAX_RESPONSE_SEGMENTS = 2;`