commands

type BenchmarkResult struct {
	Concurrency int
	MeanRPS     float64
	TotalTokens int
	TPS         float64
	TotalTime   time.Duration
	Requests    int
	TokenCounts []int
}

type BoolPtrValue struct {
	// contains filtered or unexported fields
}

type ChatResponse struct {
	Choices []struct {
		FinishReason string `json:"finish_reason"`
		Message      struct {
			Content string `json:"content"`
		} `json:"message"`
	} `json:"choices"`
	Usage struct {
		PromptTokens     int `json:"prompt_tokens"`
		CompletionTokens int `json:"completion_tokens"`
		TotalTokens      int `json:"total_tokens"`
	} `json:"usage"`
}

type CommandMetadata struct {
	Parameters []ParameterMetadata `json:"parameters"`
}

type ConfigureFlags struct {
	// Backend mode (completion, embedding, reranking)
	Mode string
	// ContextSize is the context size in tokens
	ContextSize *int32
	// Speculative decoding flags
	DraftModel        string
	NumTokens         int
	MinAcceptanceRate float64
	// vLLM-specific flags
	HFOverrides          string
	GPUMemoryUtilization *float64
	// Think parameter for reasoning models
	Think *bool
}

type Float64PtrValue struct {
	// contains filtered or unexported fields
}

type Int32PtrValue struct {
	// contains filtered or unexported fields
}

type ParameterMetadata struct {
	Name        string `json:"name"`
	Description string `json:"description"`
	Required    bool   `json:"required"`
	Type        string `json:"type"`
	Default     string `json:"default,omitempty"`
}

type ProviderMetadata struct {
	Description string          `json:"description"`
	Up          CommandMetadata `json:"up"`
	Down        CommandMetadata `json:"down"`
}

type StreamingMarkdownBuffer struct {
	// contains filtered or unexported fields
}