model

type BaseChatModel interface {
	Generate(ctx context.Context, input []*schema.Message, opts ...Option) (*schema.Message, error)
	Stream(ctx context.Context, input []*schema.Message, opts ...Option) (
		*schema.StreamReader[*schema.Message], error)
}

type CallbackInput struct {
	// Messages is the messages to be sent to the model.
	Messages []*schema.Message
	// Tools is the tools to be used in the model.
	Tools []*schema.ToolInfo
	// ToolChoice is the tool choice, which controls the tool to be used in the model.
	ToolChoice *schema.ToolChoice
	// Config is the config for the model.
	Config *Config
	// Extra is the extra information for the callback.
	Extra map[string]any
}

type CallbackOutput struct {
	// Message is the message generated by the model.
	Message *schema.Message
	// Config is the config for the model.
	Config *Config
	// TokenUsage is the token usage of this request.
	TokenUsage *TokenUsage
	// Extra is the extra information for the callback.
	Extra map[string]any
}

type CompletionTokensDetails struct {
	// ReasoningTokens tokens generated by the model for reasoning.
	// This is currently supported by OpenAI, Gemini, ARK and Qwen  chat models.
	// For other models, this field will be 0.
	ReasoningTokens int `json:"reasoning_tokens,omitempty"`
}

type Config struct {
	// Model is the model name.
	Model string
	// MaxTokens is the max number of tokens, if reached the max tokens, the model will stop generating, and mostly return an finish reason of "length".
	MaxTokens int
	// Temperature is the temperature, which controls the randomness of the model.
	Temperature float32
	// TopP is the top p, which controls the diversity of the model.
	TopP float32
	// Stop is the stop words, which controls the stopping condition of the model.
	Stop []string
}

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

type Options struct {
	// Temperature is the temperature for the model, which controls the randomness of the model.
	Temperature *float32
	// MaxTokens is the max number of tokens, if reached the max tokens, the model will stop generating, and mostly return an finish reason of "length".
	MaxTokens *int
	// Model is the model name.
	Model *string
	// TopP is the top p for the model, which controls the diversity of the model.
	TopP *float32
	// Stop is the stop words for the model, which controls the stopping condition of the model.
	Stop []string
	// Tools is a list of tools the model may call.
	Tools []*schema.ToolInfo
	// ToolChoice controls which tool is called by the model.
	ToolChoice *schema.ToolChoice
	// AllowedToolNames specifies a list of tool names that the model is allowed to call.
	// This allows for constraining the model to a specific subset of the available tools.
	AllowedToolNames []string
}

type PromptTokenDetails struct {
	// Cached tokens present in the prompt.
	CachedTokens int
}

type TokenUsage struct {
	// PromptTokens is the number of prompt tokens, including all the input tokens of this request.
	PromptTokens int
	// PromptTokenDetails is a breakdown of the prompt tokens.
	PromptTokenDetails PromptTokenDetails
	// CompletionTokens is the number of completion tokens.
	CompletionTokens int
	// TotalTokens is the total number of tokens.
	TotalTokens int
	// CompletionTokensDetails is breakdown of completion tokens.
	CompletionTokensDetails CompletionTokensDetails `json:"completion_token_details"`
}

type ToolCallingChatModel interface {
	BaseChatModel

	// WithTools returns a new ToolCallingChatModel instance with the specified tools bound.
	// This method does not modify the current instance, making it safer for concurrent use.
	WithTools(tools []*schema.ToolInfo) (ToolCallingChatModel, error)
}