Interface RateLimitConfig

Rate limiting configuration for LLM API calls.

interface RateLimitConfig {
    maxParallelRequests?: number;
    requestsPerMinute?: number;
    tokensPerMinute?: number;
}

Properties

maxParallelRequests?: number

Max concurrent LLM requests (default: 1 = serial). For future parallelization.

requestsPerMinute?: number

Max requests per minute (0 = unlimited). Provider defaults apply if not set.

tokensPerMinute?: number

Max tokens per minute (0 = unlimited). Not enforced yet — reserved for future use.