voice

type Config struct {
	// Enabled indicates whether voice processing is enabled.
	Enabled bool
	// ResponseMode controls when to respond with voice: "auto", "always", "never".
	// "auto" responds with voice when the user sends a voice message.
	ResponseMode string
	// STT configures speech-to-text.
	STT STTConfig
	// TTS configures text-to-speech.
	TTS TTSConfig
}

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

type GatewayConfig struct {
	// Provider selects the telephony provider ("twilio" or "telnyx").
	Provider string

	// Twilio configuration
	TwilioAccountSID string
	TwilioAuthToken  string
	TwilioPhone      string

	// Telnyx configuration
	TelnyxAPIKey       string
	TelnyxPhone        string
	TelnyxConnectionID string

	// Server configuration
	PublicURL  string
	ListenAddr string
	Listener   net.Listener // Optional external listener (e.g., ngrok)

	// Pipeline mode: "text" (STT→LLM→TTS, ~500-1000ms) or "realtime" (voice-to-voice, ~100-200ms)
	// Default: "text"
	Mode string

	// Voice processing (used when Mode is "text")
	Config Config

	// LLM configuration (used when Mode is "text")
	LLMProvider     string
	LLMModel        string
	LLMSystemPrompt string

	// Realtime configuration (used when Mode is "realtime")
	// RealtimeProvider: "openai" or "gemini"
	RealtimeProvider string
	RealtimeAPIKey   string
	RealtimeModel    string // e.g., "gpt-4o-realtime-preview-2024-12-17", "gemini-2.0-flash-live"
	RealtimeVoice    string // e.g., "alloy", "Puck"

	// Tools available to the voice LLM
	Tools        []ToolDefinition
	ToolHandlers map[string]ToolHandler

	// Greeting is the initial message spoken when a call connects.
	Greeting string

	// Session limits
	MaxSessionDuration time.Duration
	InterruptionMode   string

	// Logger
	Logger *slog.Logger
}

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

type STTConfig struct {
	// Provider is the STT provider name (e.g., "deepgram").
	Provider string
	// APIKey is the provider API key.
	APIKey string //nolint:gosec // G117: APIKey loaded from config file
	// Model is the provider-specific model identifier.
	Model string
	// Language is the BCP-47 language code. Empty for auto-detection.
	Language string
}

type TTSConfig struct {
	// Provider is the TTS provider name (e.g., "deepgram").
	Provider string
	// APIKey is the provider API key.
	APIKey string //nolint:gosec // G117: APIKey loaded from config file
	// Model is the provider-specific model identifier.
	Model string
	// VoiceID is the provider-specific voice identifier.
	VoiceID string
}

type ToolDefinition struct {
	Name        string         `json:"name"`
	Description string         `json:"description"`
	Parameters  map[string]any `json:"parameters"`
}

type ToolHandler func(ctx context.Context, args map[string]any) (string, error)

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