inference

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

type AdaptiveInterruptionDetectorOptions struct {
	Threshold                   *float64
	MinimumInterruptionDuration time.Duration
	MaximumAudioDuration        time.Duration
	AudioPrefixDuration         time.Duration
	DetectionInterval           time.Duration
	InferenceTimeout            time.Duration
	BaseURL                     string
	Credentials                 Credentials
	ConnectOptions              agents.APIConnectOptions
	Metadata                    func(context.Context) RequestMetadata
	WebSocketDialer             *websocket.Dialer
	InputCapacity               int
	OutputCapacity              int
	WriteTimeout                time.Duration
}

type AdaptiveInterruptionUpdateOptions struct {
	Threshold                   *float64
	MinimumInterruptionDuration *time.Duration
}

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

type AvatarSessionInfo struct {
	SessionID         string `json:"session_id,omitempty"`
	ProviderSessionID string `json:"provider_session_id,omitempty"`
	AvatarIdentity    string `json:"avatar_identity,omitempty"`
	SampleRate        int    `json:"sample_rate,omitempty"`
}

type AvatarSessionOptions struct {
	Model                     string
	AvatarParticipantIdentity string
	AvatarParticipantName     string
	LemonSlice                LemonSliceOptions
	ExtraKwargs               map[string]any
	BaseURL                   string
	Credentials               Credentials
	HTTPClient                *http.Client
	ConnectOptions            agents.APIConnectOptions
	Metadata                  RequestMetadata
	IdempotencyKey            string
}

type AvatarSessionStartOptions struct {
	LiveKitURL    string
	RoomName      string
	RoomSID       string
	AgentIdentity string
}

type Class string

type CloudTurnTransportOptions struct {
	BaseURL         string
	Credentials     Credentials
	ConnectOptions  agents.APIConnectOptions
	Metadata        func(context.Context) RequestMetadata
	WebSocketDialer *websocket.Dialer
	SendCapacity    int
	WriteTimeout    time.Duration
}

type ConnectionSettings struct {
	TimeoutSeconds float64 `json:"timeout"`
	Retries        int     `json:"retries"`
}

type Credentials struct {
	APIKey    agents.SecretString
	APISecret agents.SecretString
}

type EOTInferenceInput struct {
	PCM string `json:"pcm"`
}

type EOTInferenceOutput struct {
	Probability         float64 `json:"probability"`
	InferenceDurationMS float64 `json:"inferenceDurationMs"`
}

type FlushSentinel struct {
	Reason string
}

type InferenceVADStream struct {
	*vadpkg.BaseStream
	// contains filtered or unexported fields
}

type InterruptionDetectionError struct {
	Timestamp   time.Time
	Label       string
	Err         error
	Recoverable bool
}

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

type InterruptionStreamOptions struct {
	ConnectOptions agents.APIConnectOptions
	InputCapacity  int
	OutputCapacity int
}

type LLM struct {
	*llmpkg.Base
	// contains filtered or unexported fields
}

type LLMOptions struct {
	Model            string
	Provider         string
	BaseURL          string
	Credentials      Credentials
	ModelOptions     ModelOptions
	StrictToolSchema bool
	InferenceClass   Class
	HTTPClient       *http.Client
	Metadata         func(context.Context) RequestMetadata
}

type LemonSliceOptions struct {
	ImageURL    string
	Prompt      string
	IdlePrompt  string
	IdleTimeout *time.Duration
}

type LocalEOTPredictor interface {
	PredictEndOfTurn(context.Context, []int16) (float64, error)
	Close(context.Context) error
}

type LocalEOTPredictorFactory func(context.Context) (LocalEOTPredictor, error)

type LocalEOTPredictorFunc func(context.Context, []int16) (float64, error)

type ModelOptions map[string]any

type OverlappingSpeechEvent struct {
	Type               string        `json:"type"`
	CreatedAt          time.Time     `json:"createdAt"`
	DetectedAt         time.Time     `json:"detectedAt"`
	IsInterruption     bool          `json:"isInterruption"`
	AgentEnded         bool          `json:"agentEnded,omitempty"`
	TotalDuration      time.Duration `json:"-"`
	PredictionDuration time.Duration `json:"-"`
	DetectionDelay     time.Duration `json:"-"`
	OverlapStartedAt   *time.Time    `json:"-"`
	SpeechInput        []int16       `json:"-"`
	Probabilities      []float32     `json:"-"`
	Probability        float64       `json:"probability"`
	NumRequests        int64         `json:"numRequests"`
}

type RequestMetadata struct {
	RoomID      string
	JobID       string
	AgentID     string
	WorkerToken agents.SecretString
}

type STT struct {
	*stt.Base
	// contains filtered or unexported fields
}

type STTFallback struct {
	Models []STTFallbackModel `json:"models"`
}

type STTFallbackModel struct {
	Model string       `json:"model"`
	Extra ModelOptions `json:"extra,omitempty"`
}

type STTOptions struct {
	Model           string
	Language        agents.LanguageCode
	Encoding        string
	SampleRate      int
	BaseURL         string
	Credentials     Credentials
	ModelOptions    ModelOptions
	Fallback        []STTFallbackModel
	ConnectOptions  agents.APIConnectOptions
	Metadata        func(context.Context) RequestMetadata
	WebSocketDialer *websocket.Dialer
	InputCapacity   int
	OutputCapacity  int
	MaxMessageBytes int64
	SessionKeyterms []string
}

type STTServerEvent struct {
	Type       string          `json:"type"`
	SessionID  string          `json:"session_id,omitempty"`
	Transcript string          `json:"transcript,omitempty"`
	Language   string          `json:"language,omitempty"`
	Start      float64         `json:"start,omitempty"`
	Duration   float64         `json:"duration,omitempty"`
	Confidence float64         `json:"confidence,omitempty"`
	Words      []STTWord       `json:"words,omitempty"`
	SpeakerID  *string         `json:"speaker_id,omitempty"`
	Extra      json.RawMessage `json:"extra,omitempty"`
	Message    string          `json:"message,omitempty"`
	Code       *int            `json:"code,omitempty"`
	Unknown    json.RawMessage `json:"-"`
}

type STTSessionCreate struct {
	Type       string              `json:"type"`
	Model      string              `json:"model,omitempty"`
	Settings   STTSettings         `json:"settings"`
	Fallback   *STTFallback        `json:"fallback,omitempty"`
	Connection *ConnectionSettings `json:"connection,omitempty"`
}

type STTSessionUpdate struct {
	Type     string            `json:"type"`
	Settings STTUpdateSettings `json:"settings"`
}

type STTSettings struct {
	SampleRate string       `json:"sample_rate"`
	Encoding   string       `json:"encoding"`
	Language   string       `json:"language,omitempty"`
	Extra      ModelOptions `json:"extra"`
}

type STTUpdateOptions struct {
	Model        *string
	Language     *agents.LanguageCode
	ModelOptions ModelOptions
}

type STTUpdateSettings struct {
	Model    string       `json:"model,omitempty"`
	Language string       `json:"language,omitempty"`
	Extra    ModelOptions `json:"extra,omitempty"`
}

type STTWord struct {
	Word       string          `json:"word"`
	Start      float64         `json:"start"`
	End        float64         `json:"end"`
	Confidence float64         `json:"confidence"`
	SpeakerID  *string         `json:"speaker_id,omitempty"`
	Extra      json.RawMessage `json:"extra,omitempty"`
}

type SpeechStream struct {
	*stt.BaseStream
	// contains filtered or unexported fields
}

type StreamingTurnDetectionTransport interface {
	Attach(*TurnDetectorStream)
	Run(context.Context) error
	RunInference(context.Context, string) error
	PushFrame(context.Context, agents.AudioFrame) error
	Flush(context.Context, FlushSentinel) error
	Close() error
}

type SynthesizeStream struct {
	*tts.BaseSynthesizeStream
	// contains filtered or unexported fields
}

type TTS struct {
	*tts.Base
	// contains filtered or unexported fields
}

type TTSAlignmentDecoder interface {
	DecodeTTSAlignment(context.Context, TTSServerEvent, string) ([]agents.TimedString, error)
}

type TTSAlignmentDecoderFunc func(context.Context, TTSServerEvent, string) ([]agents.TimedString, error)

type TTSCharTimestamp struct {
	Char  string  `json:"char"`
	Start float64 `json:"start"`
	End   float64 `json:"end"`
}

type TTSFallback struct {
	Models []TTSFallbackModel `json:"models"`
}

type TTSFallbackModel struct {
	Model string       `json:"model"`
	Voice string       `json:"voice"`
	Extra ModelOptions `json:"extra,omitempty"`
}

type TTSGenerationConfig struct {
	Voice    string `json:"voice,omitempty"`
	Language string `json:"language,omitempty"`
	Model    string `json:"model,omitempty"`
}

type TTSInputTranscript struct {
	Type             string               `json:"type"`
	Transcript       string               `json:"transcript"`
	GenerationConfig *TTSGenerationConfig `json:"generation_config,omitempty"`
	Extra            ModelOptions         `json:"extra,omitempty"`
}

type TTSOptions struct {
	Model              string
	Voice              string
	Language           agents.LanguageCode
	Encoding           string
	SampleRate         int
	BaseURL            string
	Credentials        Credentials
	ModelOptions       ModelOptions
	Fallback           []TTSFallbackModel
	ConnectOptions     agents.APIConnectOptions
	Metadata           func(context.Context) RequestMetadata
	WebSocketDialer    *websocket.Dialer
	InputCapacity      int
	OutputCapacity     int
	MaxMessageBytes    int64
	MaxSessionDuration time.Duration
	// AlignmentDecoder customizes provider timestamp decoding. Nil uses the
	// cross-SDK Cloud Inference word/character decoder.
	AlignmentDecoder TTSAlignmentDecoder
	// MaxPendingAlignmentTokens bounds timestamp messages received before an
	// audio frame. Zero selects a production default.
	MaxPendingAlignmentTokens int
}

type TTSServerEvent struct {
	Type      string             `json:"type"`
	SessionID string             `json:"session_id,omitempty"`
	Audio     string             `json:"audio,omitempty"`
	Message   string             `json:"message,omitempty"`
	Words     []TTSWordTimestamp `json:"words,omitempty"`
	Chars     []TTSCharTimestamp `json:"chars,omitempty"`
	Unknown   json.RawMessage    `json:"-"`
}

type TTSSessionCreate struct {
	Type       string              `json:"type"`
	SampleRate string              `json:"sample_rate"`
	Encoding   string              `json:"encoding"`
	Model      string              `json:"model,omitempty"`
	Voice      string              `json:"voice,omitempty"`
	Language   string              `json:"language,omitempty"`
	Extra      ModelOptions        `json:"extra"`
	Transcript string              `json:"transcript,omitempty"`
	Fallback   *TTSFallback        `json:"fallback,omitempty"`
	Connection *ConnectionSettings `json:"connection,omitempty"`
}

type TTSUpdateOptions struct {
	Model        *string
	Voice        *string
	Language     *agents.LanguageCode
	ModelOptions ModelOptions
}

type TTSWordTimestamp struct {
	Word  string  `json:"word"`
	Start float64 `json:"start"`
	End   float64 `json:"end"`
}

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

type ThresholdOverride struct {
	Scalar    *float64           `json:"-"`
	Languages map[string]float64 `json:"-"`
}

type ThresholdSnapshot struct {
	Model                TurnDetectorModel  `json:"model"`
	Thresholds           map[string]float64 `json:"thresholds"`
	DefaultThreshold     *float64           `json:"defaultThreshold,omitempty"`
	Overrides            ThresholdOverride  `json:"overrides,omitzero"`
	BackchannelOverrides ThresholdOverride  `json:"backchannelOverrides,omitzero"`
}

type TurnDetectionEvent struct {
	Type                   string         `json:"type"`
	EndOfTurnProbability   float64        `json:"endOfTurnProbability"`
	LastSpeakingTime       time.Time      `json:"-"`
	LastSpeakingTimeMillis int64          `json:"lastSpeakingTimeMs"`
	DetectionDelay         *time.Duration `json:"-"`
	InferenceDuration      *time.Duration `json:"-"`
	BackchannelProbability *float64       `json:"backchannelProbability,omitempty"`
}

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

type TurnDetectorModel string

type TurnDetectorOptions struct {
	Version               TurnDetectorVersion
	UnlikelyThreshold     ThresholdOverride
	BackchannelThreshold  ThresholdOverride
	BaseURL               string
	Credentials           Credentials
	SampleRate            int
	ConnectOptions        agents.APIConnectOptions
	Metadata              func(context.Context) RequestMetadata
	WebSocketDialer       *websocket.Dialer
	LocalPredictor        LocalEOTPredictor
	LocalPredictorFactory LocalEOTPredictorFactory
	// Executor selects the worker-global runner registered under
	// EOTInferenceMethod. When nil, local fallback discovers an executor from
	// the stream context propagated by JobContext.
	Executor               ipc.InferenceExecutor
	KeepLocalPredictorOpen bool
	InputCapacity          int
}

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

type TurnDetectorStreamOptions struct {
	ConnectOptions agents.APIConnectOptions
	InputCapacity  int
	Transport      StreamingTurnDetectionTransport
}

type TurnDetectorUpdateOptions struct {
	UnlikelyThreshold    *ThresholdOverride
	BackchannelThreshold *ThresholdOverride
}

type TurnDetectorVersion string

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

type TurnPredictionDetails struct {
	InferenceDuration      *time.Duration
	DetectionDelay         *time.Duration
	BackchannelProbability *float64
}

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

type VADInferenceInput struct {
	StreamID  string                `json:"streamId"`
	Operation VADInferenceOperation `json:"operation"`
	PCM       []byte                `json:"pcm,omitempty"`
}

type VADInferenceOperation string

type VADInferenceOutput struct {
	Probability   float64 `json:"probability"`
	WindowSamples int     `json:"windowSamples,omitempty"`
}

type VADModel string

type VADOptions struct {
	Model                  VADModel
	MinimumSpeechDuration  time.Duration
	MinimumSilenceDuration time.Duration
	PrefixPaddingDuration  time.Duration
	MaximumBufferedSpeech  time.Duration
	ActivationThreshold    float64
	DeactivationThreshold  *float64
	PredictorFactory       VADPredictorFactory
	// Executor selects the worker-global runner registered under
	// VADInferenceMethod. When nil, each stream discovers the executor from
	// its context, matching TurnDetector and process-isolated job behavior.
	// PredictorFactory and Executor are mutually exclusive.
	Executor       ipc.InferenceExecutor
	StreamCapacity int
}

type VADPredictor interface {
	WindowSamples() int
	Predict(context.Context, []int16) (float64, error)
	Reset() error
	Close() error
}

type VADPredictorFactory func(context.Context) (VADPredictor, error)

type VADUpdateOptions struct {
	MinimumSpeechDuration  *time.Duration
	MinimumSilenceDuration *time.Duration
	PrefixPaddingDuration  *time.Duration
	MaximumBufferedSpeech  *time.Duration
	ActivationThreshold    *float64
	DeactivationThreshold  *float64
}