speechkit

type AssistRequest struct {
	Text              string                     `json:"text"`
	Locale            string                     `json:"locale,omitempty"`
	Selection         string                     `json:"selection,omitempty"`
	Context           string                     `json:"context,omitempty"`
	EditableTarget    bool                       `json:"editableTarget,omitempty"`
	ProviderProfileID string                     `json:"providerProfileId,omitempty"`
	SessionKey        string                     `json:"sessionKey,omitempty"`
	SpeakerOptions    speaker.Options            `json:"speakerOptions,omitempty"`
	Speakers          *speaker.DiarizationResult `json:"speakers,omitempty"`
}

type AssistResult struct {
	Text       string                     `json:"text"`
	SpeakText  string                     `json:"speakText,omitempty"`
	Action     string                     `json:"action,omitempty"`
	Kind       string                     `json:"kind,omitempty"`
	Surface    AssistSurfaceDecision      `json:"surface"`
	ShortcutID string                     `json:"shortcutId,omitempty"`
	Locale     string                     `json:"locale,omitempty"`
	MessageID  localization.MessageID     `json:"messageId,omitempty"`
	ReasonCode string                     `json:"reasonCode,omitempty"`
	Audio      *AudioData                 `json:"audio,omitempty"`
	Format     string                     `json:"format,omitempty"`
	Speakers   *speaker.DiarizationResult `json:"speakers,omitempty"`
}

type AssistService interface {
	Process(context.Context, AssistRequest) (AssistResult, error)
}

type AssistSetting struct {
	ModeSetting
	TTSEnabled      bool   `json:"ttsEnabled"`
	UtilityRegistry string `json:"utilityRegistry,omitempty"`
}

type AssistSurfaceDecision string

type Attr struct {
	Key   string
	Value any
}

type AudioData []byte

type AudioIdleObserver interface {
	IdleAudio() (silence time.Duration, lastFrame time.Time)
}

type AudioRecorder interface {
	Start() error
	Stop() ([]byte, error)
	SetPCMHandler(func([]byte))
}

type AudioSegment struct {
	PCM       []byte
	Duration  time.Duration
	Paragraph bool
	Final     bool
}

type Capability string

type Command struct {
	Type     CommandType
	Text     string
	NoteID   int64
	Target   string
	Metadata map[string]string
}

type CommandBus interface {
	Dispatch(context.Context, Command) error
}

type CommandType string

type CommitObserver interface {
	OnCommit(completion Completion)
}

type Completion struct {
	Transcript             Transcript
	QuickNoteCommitted     bool
	QuickNoteCreated       bool
	QuickNoteID            int64
	TranscriptionPersisted bool
	AudioDurationMs        int64
}

type CustomizationAction struct {
	ReplacementID string         `json:"replacement_id,omitempty"`
	Kind          string         `json:"kind,omitempty"`
	Intent        string         `json:"intent,omitempty"`
	Text          string         `json:"text,omitempty"`
	Template      string         `json:"template,omitempty"`
	Payload       map[string]any `json:"payload,omitempty"`
	MatchedText   string         `json:"matched_text,omitempty"`
	Count         int            `json:"count,omitempty"`
}

type DictationRun struct {
	ID               string                     `json:"id,omitempty"`
	Transcript       Transcript                 `json:"transcript"`
	StartedAt        time.Time                  `json:"startedAt,omitempty"`
	CompletedAt      time.Time                  `json:"completedAt,omitempty"`
	ProviderProfile  string                     `json:"providerProfile,omitempty"`
	DictionaryTerms  []string                   `json:"dictionaryTerms,omitempty"`
	AudioDurationMs  int64                      `json:"audioDurationMs,omitempty"`
	ProcessingTimeMs int64                      `json:"processingTimeMs,omitempty"`
	Speakers         *speaker.DiarizationResult `json:"speakers,omitempty"`
}

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

type DictationService interface {
	Start(context.Context) error
	Stop(context.Context) (DictationRun, error)
}

type DictationSetting struct {
	ModeSetting
	DictionaryEnabled bool `json:"dictionaryEnabled"`
}

type DictationStream interface {
	SendPCM(ctx context.Context, pcm []byte) error
	Finalize(ctx context.Context) error
	Receive(ctx context.Context) (DictationStreamEvent, error)
	Close() error
}

type DictationStreamEvent struct {
	Sequence       int64
	SessionID      uint64
	SegmentID      uint64
	ProviderItemID string
	Text           string
	IsFinal        bool
	Language       string
	Provider       string
	Model          string
	Confidence     float64
	Words          []WordConfidence
	Speakers       *speaker.DiarizationResult
}

type DictationStreamOptions struct {
	SessionID         uint64
	ProviderProfileID string
	Language          string
	Model             string
	InterimResults    bool
	EndpointingMs     int
	TurnDetection     bool
	Keyterms          []string
	PromptHint        string
	Diarization       bool
}

type DictationStreamProvider interface {
	StartDictationStream(ctx context.Context, opts DictationStreamOptions, format speaker.AudioFormat) (DictationStream, error)
}

type DictationStreamSink interface {
	HandleDictationStreamEvent(ctx context.Context, event DictationStreamEvent, opts DictationStreamSinkOptions) error
}

type DictationStreamSinkOptions struct {
	Target             any
	QuickNote          bool
	QuickNoteID        int64
	Language           string
	RecordingSessionID int64
	// CaptureChannel names the capture source feeding this stream, and
	// CaptureEpoch is the wall clock the session's timeline is measured from.
	// Sinks stamp final events with the elapsed offset so parallel channels of
	// one meeting can be interleaved. A zero epoch disables the timeline.
	CaptureChannel string
	CaptureEpoch   time.Time
}

type Engine interface {
	Start(context.Context) error
	Stop(context.Context) error
	Events() <-chan Event
	Commands() CommandBus
	State() Snapshot
}

type Event struct {
	Type                 EventType
	Time                 time.Time
	Message              string
	Text                 string
	Provider             string
	Mode                 string
	SessionID            string
	QuickNote            bool
	Err                  error
	Shortcut             string
	Metadata             *Metadata
	CustomizationActions []CustomizationAction
}

type EventType string

type ExecutionMode string

type Hooks struct {
	Start         func(context.Context) error
	Stop          func(context.Context) error
	HandleCommand func(context.Context, Command) error
}

type IdleObserver interface {
	IdleSince() time.Time
}

type IntelligenceKind string

type JobSubmitter interface {
	Submit(TranscriptionJob) error
}

type LiveCommitFlusher interface {
	FlushLiveCommit(ctx context.Context) error
}

type LiveCommitPolicy struct {
	Mode         string
	MinSentences int
	Hold         time.Duration
}

type Metadata map[string]string

type Modality string

type Mode string

type ModeBehavior string

type ModeContract struct {
	Mode         Mode             `json:"mode"`
	Intelligence IntelligenceKind `json:"intelligence"`
	Input        string           `json:"input"`
	Output       string           `json:"output"`
	Allowed      []Capability     `json:"allowed"`
	Forbidden    []Capability     `json:"forbidden"`
}

type ModeSetting struct {
	Enabled           bool   `json:"enabled"`
	Hotkey            string `json:"hotkey,omitempty"`
	HotkeyBehavior    string `json:"hotkeyBehavior,omitempty"`
	PrimaryProfileID  string `json:"primaryProfileId,omitempty"`
	FallbackProfileID string `json:"fallbackProfileId,omitempty"`
	// ModeSource is "local" (default) or "server". When "server", this mode
	// runs against the speechkit-server pointed to by ServerConnection
	// instead of the in-process Framework kernel. Empty/missing is treated
	// as "local" for backwards compatibility with pre-0.26 hosts.
	ModeSource string `json:"modeSource,omitempty"`
}

type ModeSettings struct {
	Dictation        DictationSetting        `json:"dictation"`
	Assist           AssistSetting           `json:"assist"`
	VoiceAgent       VoiceAgentSetting       `json:"voiceAgent"`
	ServerConnection ServerConnectionSetting `json:"serverConnection"`
}

type ModelLifecycle string

type ModelVariant struct {
	ID          string `json:"id"`
	Name        string `json:"name"`
	ModelID     string `json:"modelId"`
	Description string `json:"description,omitempty"`
	Recommended bool   `json:"recommended,omitempty"`
}

type Persistence interface {
	QuickNoteStore
	TranscriptionStore
}

type PooledPCMRecorder interface {
	SetPooledPCMHandler(func(buf []byte, release func()))
}

type ProviderDefault struct {
	Provider           string              `json:"provider"`
	DisplayName        string              `json:"displayName"`
	Mode               Mode                `json:"mode"`
	ProfileID          string              `json:"profileId"`
	ModelID            string              `json:"modelId,omitempty"`
	ProviderKind       ProviderKind        `json:"providerKind"`
	ExecutionMode      ExecutionMode       `json:"executionMode,omitempty"`
	Support            ProviderSupportKind `json:"support"`
	Capabilities       []Capability        `json:"capabilities,omitempty"`
	NativeOptions      []string            `json:"nativeOptions,omitempty"`
	AuthRequirement    string              `json:"authRequirement,omitempty"`
	CredentialRequired bool                `json:"credentialRequired"`
	CredentialTarget   string              `json:"credentialTarget,omitempty"`
	Transport          string              `json:"transport,omitempty"`
	EvidenceURL        string              `json:"evidenceUrl,omitempty"`
	Default            bool                `json:"default,omitempty"`
	Recommended        bool                `json:"recommended,omitempty"`
	Experimental       bool                `json:"experimental,omitempty"`
	Variants           []ModelVariant      `json:"variants,omitempty"`
}

type ProviderFeature string

type ProviderFeatureSupport struct {
	Feature       ProviderFeature     `json:"feature"`
	Support       ProviderSupportKind `json:"support"`
	Mode          Mode                `json:"mode,omitempty"`
	ProfileID     string              `json:"profileId,omitempty"`
	ModelID       string              `json:"modelId,omitempty"`
	NativeOptions []string            `json:"nativeOptions,omitempty"`
	EvidenceURL   string              `json:"evidenceUrl,omitempty"`
}

type ProviderKind string

type ProviderMatrixRow struct {
	Provider    string                   `json:"provider"`
	DisplayName string                   `json:"displayName"`
	Profiles    []ProviderDefault        `json:"profiles"`
	Features    []ProviderFeatureSupport `json:"features"`
}

type ProviderModelDescriptor struct {
	Provider    string         `json:"provider"`
	ModelID     string         `json:"modelId"`
	ProfileID   string         `json:"profileId,omitempty"`
	Mode        Mode           `json:"mode"`
	Name        string         `json:"name"`
	Lifecycle   ModelLifecycle `json:"lifecycle"`
	Default     bool           `json:"default,omitempty"`
	Recommended bool           `json:"recommended,omitempty"`
	SourceURL   string         `json:"sourceUrl"`

	// Freshness metadata (kombify-SpeechKit-glnc). Dates are calendar days
	// (YYYY-MM-DD) from vendor documentation. LastVerifiedAt is the day the
	// row was last checked against those docs; TestDefaultModelRegistryFreshnessSLA
	// fails when a default/recommended row is missing it or older than
	// ModelFreshnessSLA.
	ReleasedAt           string `json:"releasedAt,omitempty"`
	DeprecatedAt         string `json:"deprecatedAt,omitempty"`
	SunsetAt             string `json:"sunsetAt,omitempty"`
	LastVerifiedAt       string `json:"lastVerifiedAt,omitempty"`
	MultilanguageCapable bool   `json:"multilanguageCapable,omitempty"`
}

type ProviderProfile struct {
	ID   string `json:"id"`
	Mode Mode   `json:"mode"`
	// Modality is what the entry does. ProviderProfileWithDefaults derives it
	// from Mode when unset, and derives Mode from it for support entries that
	// carry no mode.
	Modality         Modality       `json:"modality,omitempty"`
	Name             string         `json:"name"`
	ProviderKind     ProviderKind   `json:"providerKind"`
	ExecutionMode    ExecutionMode  `json:"executionMode,omitempty"`
	Provider         string         `json:"provider,omitempty"`
	ModelID          string         `json:"modelId,omitempty"`
	Lifecycle        ModelLifecycle `json:"lifecycle,omitempty"`
	Source           string         `json:"source,omitempty"`
	Description      string         `json:"description,omitempty"`
	License          string         `json:"license,omitempty"`
	Capabilities     []Capability   `json:"capabilities,omitempty"`
	SupportedLocales []string       `json:"supportedLocales,omitempty"`
	NativeOptions    []string       `json:"nativeOptions,omitempty"`
	AuthRequirement  string         `json:"authRequirement,omitempty"`
	Transport        string         `json:"transport,omitempty"`
	EvidenceURL      string         `json:"evidenceUrl,omitempty"`
	AdapterKind      string         `json:"adapterKind,omitempty"`
	Variants         []ModelVariant `json:"variants,omitempty"`
	AllowInference   bool           `json:"inferenceAllowed,omitempty"`
	Default          bool           `json:"default,omitempty"`
	Recommended      bool           `json:"recommended,omitempty"`
	Experimental     bool           `json:"experimental,omitempty"`
}

type ProviderSupportKind string

type QuickNoteStore interface {
	SaveQuickNote(ctx context.Context, text, language, provider string, durationMs, latencyMs int64, audioData []byte) (int64, error)
	GetQuickNoteText(ctx context.Context, id int64) (string, error)
	UpdateQuickNote(ctx context.Context, id int64, text string) error
	UpdateQuickNoteCapture(ctx context.Context, id int64, text, provider string, durationMs, latencyMs int64, audioData []byte) error
}

type Readiness struct {
	SchemaVersion    string                 `json:"schemaVersion,omitempty"`
	ProfileID        string                 `json:"profileId"`
	Mode             Mode                   `json:"mode"`
	ProviderKind     ProviderKind           `json:"providerKind"`
	ExecutionMode    ExecutionMode          `json:"executionMode,omitempty"`
	ModelID          string                 `json:"modelId,omitempty"`
	Source           string                 `json:"source,omitempty"`
	Active           bool                   `json:"active"`
	Default          bool                   `json:"default"`
	Configured       bool                   `json:"configured"`
	CredentialsReady bool                   `json:"credentialsReady"`
	RuntimeReady     bool                   `json:"runtimeReady"`
	CapabilityReady  bool                   `json:"capabilityReady"`
	Ready            bool                   `json:"ready"`
	Missing          []string               `json:"missing,omitempty"`
	Requirements     []ReadinessRequirement `json:"requirements,omitempty"`
	Actions          []ReadinessAction      `json:"actions,omitempty"`
	Artifacts        []ReadinessArtifact    `json:"artifacts,omitempty"`
}

type ReadinessAction struct {
	ID     string `json:"id"`
	Label  string `json:"label"`
	Kind   string `json:"kind"`
	Target string `json:"target,omitempty"`
}

type ReadinessArtifact struct {
	ID             string `json:"id"`
	Name           string `json:"name"`
	Kind           string `json:"kind"`
	SizeLabel      string `json:"sizeLabel,omitempty"`
	SizeBytes      int64  `json:"sizeBytes,omitempty"`
	Available      bool   `json:"available"`
	Selected       bool   `json:"selected"`
	RuntimeReady   bool   `json:"runtimeReady,omitempty"`
	RuntimeProblem string `json:"runtimeProblem,omitempty"`
	Recommended    bool   `json:"recommended,omitempty"`
}

type ReadinessRequirement struct {
	ID       string `json:"id"`
	Label    string `json:"label"`
	Category string `json:"category"`
	Required bool   `json:"required"`
	Ready    bool   `json:"ready"`
	Missing  string `json:"missing,omitempty"`
}

type ReadySegmentCollector interface {
	SegmentCollector
	DrainReadySegments() []AudioSegment
}

type RecordingCancelOptions struct {
	Label string
}

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

type RecordingObserver interface {
	OnState(status, text string)
	OnLog(message, kind string)
}

type RecordingStartOptions struct {
	// Context scopes provider-native streaming sessions. When nil,
	// context.Background is used.
	Context     context.Context
	Label       string
	Target      any
	Language    string
	QuickNote   bool
	QuickNoteID int64
	// RecordingSessionID links final transcript commits to a persisted
	// long-running dictation or meeting session owned by the host.
	RecordingSessionID int64
	// CaptureChannel names the audio source this controller records, so a host
	// running several controllers over one recording session — meeting capture
	// records the microphone and the system loopback at the same time — can tell
	// the resulting transcripts apart. See CaptureChannel*.
	CaptureChannel string
	// CaptureEpoch is the wall clock that transcript timestamps are measured
	// from. Hosts recording one session across several controllers pass the same
	// epoch to all of them so the transcripts interleave on a single timeline.
	// Zero means "start of this recording".
	CaptureEpoch time.Time
	// StreamSegments enables live-ish dictation for this recording session.
	// Completed pause-bounded segments are queued before Stop(); Stop() then
	// flushes only pending/remaining tail segments. Leave false for Assist and
	// Voice Agent fallback capture, where a single full turn is the safer unit.
	StreamSegments bool
	// ProviderStream enables provider-native realtime dictation when the host
	// configured a DictationStreamProvider and DictationStreamSink. If stream
	// startup fails, the controller keeps using StreamSegments/full-capture
	// fallback behavior.
	ProviderStream bool
	// DictationStreamOptions are passed to the native provider stream. SessionID
	// and Language are filled from the active recording when left empty.
	DictationStreamOptions DictationStreamOptions
	// LiveCommitMode groups provider-finals before field injection.
	// Empty keeps immediate commit (tests and hosts that do not opt in).
	// Desktop dictation defaults to LiveCommitPassage.
	LiveCommitMode string
	// IdleTimeout, when greater than zero AND the underlying collector
	// implements [IdleObserver], arms a watcher that calls
	// OnIdleTimeoutCallback once the user has been silent for this long.
	// Zero (default) disables the watcher — typical for hold-to-talk
	// hotkey sessions that already terminate on KeyUp.
	IdleTimeout time.Duration
	// OnIdleTimeoutCallback fires once if IdleTimeout elapses without
	// observed speech. Wired by the host to dispatch a Stop command so
	// the dictate session ends after a silence window. The watcher
	// guarantees at-most-one invocation per Start() call.
	OnIdleTimeoutCallback func()
}

type RecordingStopOptions struct {
	Label string
	// TailDelay keeps the recorder physically open for a short grace period
	// after a stop request. Hold-to-talk callers use this to avoid clipping
	// final syllables when the shortcut is released a few milliseconds early.
	TailDelay time.Duration
}

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

type RuntimePolicy struct {
	EnabledModes    []Mode                `json:"enabledModes,omitempty"`
	AllowedProfiles []string              `json:"allowedProfiles,omitempty"`
	FixedProfiles   map[Mode]string       `json:"fixedProfiles,omitempty"`
	AllowFallbacks  bool                  `json:"allowFallbacks,omitempty"`
	ModeBehaviors   map[Mode]ModeBehavior `json:"modeBehaviors,omitempty"`
}

type SegmentCollector interface {
	FeedPCM([]byte) error
	CollectStopSegments(fullPCM []byte) ([]AudioSegment, error)
}

type SegmentCollectorFactory func() SegmentCollector

type ServerConnectionSetting struct {
	Enabled              bool                     `json:"enabled"`
	ActiveTargetID       string                   `json:"activeTargetId,omitempty"`
	URL                  string                   `json:"url"`
	BearerTokenEnv       string                   `json:"bearerTokenEnv,omitempty"`
	AuthMode             string                   `json:"authMode,omitempty"`
	BetaInstallIDEnv     string                   `json:"betaInstallIdEnv,omitempty"`
	BetaInstallSecretEnv string                   `json:"betaInstallSecretEnv,omitempty"`
	BearerTokenSet       bool                     `json:"bearerTokenSet"`
	FallbackToLocal      bool                     `json:"fallbackToLocal"`
	RequestTimeoutSec    int                      `json:"requestTimeoutSec"`
	Targets              []ServerConnectionTarget `json:"targets,omitempty"`
}

type ServerConnectionTarget struct {
	ID                   string `json:"id"`
	Label                string `json:"label"`
	URL                  string `json:"url"`
	AuthMode             string `json:"authMode"`
	BearerTokenEnv       string `json:"bearerTokenEnv,omitempty"`
	BetaInstallIDEnv     string `json:"betaInstallIdEnv,omitempty"`
	BetaInstallSecretEnv string `json:"betaInstallSecretEnv,omitempty"`
	BearerTokenSet       bool   `json:"bearerTokenSet"`
	FallbackToLocal      bool   `json:"fallbackToLocal"`
	RequestTimeoutSec    int    `json:"requestTimeoutSec"`
}

type Snapshot struct {
	Status                string
	Text                  string
	Level                 float64
	Hotkey                string
	ActiveMode            string
	Providers             []string
	ActiveProfiles        map[string]string
	Transcriptions        int
	QuickNoteMode         bool
	QuickCaptureMode      bool
	LastTranscriptionText string
}

type Submission struct {
	PCM          []byte
	WAV          []byte
	DurationSecs float64
	Language     string
	Prefix       string
	QuickNote    bool
	QuickNoteID  int64
	SessionID    uint64
	SegmentID    uint64
	// RecordingSessionID is copied into the final Transcript and Completion so
	// host observers can attach committed text to a long-running session after
	// persistence/output succeeds.
	RecordingSessionID int64
	// CaptureChannel, CapturedStartMs and CapturedEndMs carry the capture
	// source and wall-clock placement through to the Transcript. See the
	// matching Transcript fields.
	CaptureChannel  string
	CapturedStartMs int64
	CapturedEndMs   int64
	// ProviderItemID carries provider-native turn/item IDs for realtime
	// streams. Segment-batch jobs leave it empty and rely on SessionID+SegmentID.
	ProviderItemID string
	SegmentFinal   bool
	// QueuedAt is set by TranscriptionWorker.Submit when the segment enters
	// the worker queue. Hosts can prefill it when replaying externally queued
	// work, but ordinary callers should leave it zero.
	QueuedAt time.Time
}

type Transcriber interface {
	Transcribe(ctx context.Context, audio []byte, durationSecs float64, language string) (Transcript, error)
}

type Transcript struct {
	Text       string
	Language   string
	Duration   time.Duration
	Provider   string
	Model      string
	Confidence float64
	// Session metadata is set for progressive dictation/meeting pipelines.
	// Draft transcripts may be replaced by later revisions; only final
	// segment IDs are committed by the worker ledger.
	SessionID      uint64
	SegmentID      uint64
	ProviderItemID string
	SegmentFinal   bool
	// RecordingSessionID links this transcript to a persisted long-running
	// dictation or meeting session in the host store.
	RecordingSessionID int64
	// CaptureChannel names the capture source this transcript came from (see
	// CaptureChannel*). Sessions that record more than one source at once —
	// meeting capture runs the microphone and the system loopback in parallel —
	// use it to keep the two apart. Empty for single-source captures.
	CaptureChannel string
	// CapturedStartMs and CapturedEndMs place this transcript on the capture
	// session's wall-clock timeline, relative to RecordingStartOptions.
	// CaptureEpoch. Both are zero when the host did not request a timeline.
	CapturedStartMs int64
	CapturedEndMs   int64
	// Words carries per-word acoustic confidence when available (Deepgram,
	// AssemblyAI). Used to surface likely-misrecognized terms; nil otherwise.
	Words                []WordConfidence
	Speakers             *speaker.DiarizationResult
	CustomizationActions []CustomizationAction `json:"customization_actions,omitempty"`
}

type TranscriptInterceptor interface {
	Intercept(ctx context.Context, transcript Transcript, target any) (bool, error)
}

type TranscriptOutput interface {
	Deliver(ctx context.Context, transcript Transcript, target any) error
}

type TranscriptSegmentKey struct {
	CaptureChannel string
	SessionID      uint64
	SegmentID      uint64
	ProviderItemID string
}

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

type TranscriptTransformer interface {
	Transform(ctx context.Context, transcript Transcript) (Transcript, error)
}

type TranscriptionDraftObserver interface {
	OnTranscriptDraft(transcript Transcript)
}

type TranscriptionJob struct {
	Submission
	Segments []Submission
	Target   any
}

type TranscriptionObserver interface {
	OnState(status, text string)
	OnLog(message, kind string)
	OnTranscriptCommitted(transcript Transcript, quickNote bool)
}

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

type TranscriptionStore interface {
	SaveTranscription(ctx context.Context, text, language, provider, model string, durationMs, latencyMs int64, audioData []byte) error
}

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

type TranscriptionWorkerConfig struct {
	Timeout     time.Duration
	QueueSize   int
	Runner      *TranscriptionRunner
	Output      TranscriptOutput
	Interceptor TranscriptInterceptor
	Transformer TranscriptTransformer
	Observer    TranscriptionObserver
	Ledger      *TranscriptSessionLedger
	// LowConfidenceThreshold flags recognized words below this acoustic
	// confidence (0..1) so the host can surface likely-misrecognized terms.
	// <= 0 disables the check. Only providers that expose per-word confidence
	// (Deepgram, AssemblyAI) produce data here.
	LowConfidenceThreshold float64
}

type VoiceActivityDetector interface {
	ProcessFrame([]int16) (float32, error)
	Reset()
}

type VoiceAgentService interface {
	Start(context.Context) error
	Stop(context.Context) (VoiceAgentSession, error)
	SendText(context.Context, string) error
	CurrentSession(context.Context) (VoiceAgentSession, error)
}

type VoiceAgentSession struct {
	ID                string                     `json:"id,omitempty"`
	StartedAt         time.Time                  `json:"startedAt,omitempty"`
	EndedAt           time.Time                  `json:"endedAt,omitempty"`
	Locale            string                     `json:"locale,omitempty"`
	ProviderProfileID string                     `json:"providerProfileId,omitempty"`
	RuntimeKind       string                     `json:"runtimeKind,omitempty"`
	Turns             []VoiceAgentTurn           `json:"turns,omitempty"`
	Summary           VoiceAgentSessionSummary   `json:"summary"`
	Speakers          *speaker.DiarizationResult `json:"speakers,omitempty"`
}

type VoiceAgentSessionSummary struct {
	Title         string   `json:"title,omitempty"`
	Summary       string   `json:"summary"`
	Ideas         []string `json:"ideas,omitempty"`
	Decisions     []string `json:"decisions,omitempty"`
	OpenQuestions []string `json:"openQuestions,omitempty"`
	NextSteps     []string `json:"nextSteps,omitempty"`
	RawText       string   `json:"rawText,omitempty"`
}

type VoiceAgentSetting struct {
	ModeSetting
	SessionSummary   bool   `json:"sessionSummary"`
	PipelineFallback bool   `json:"pipelineFallback"`
	CloseBehavior    string `json:"closeBehavior,omitempty"`
	AgentProfileID   string `json:"agentProfileId,omitempty"`
	AgentSequenceID  string `json:"agentSequenceId,omitempty"`
}

type VoiceAgentTurn struct {
	Role              string    `json:"role"`
	Text              string    `json:"text"`
	CreatedAt         time.Time `json:"createdAt,omitempty"`
	SpeakerLabel      string    `json:"speakerLabel,omitempty"`
	PersonID          string    `json:"personId,omitempty"`
	DisplayName       string    `json:"displayName,omitempty"`
	SpeakerConfidence float64   `json:"speakerConfidence,omitempty"`
}

type WordConfidence struct {
	Text       string
	Confidence float64
	StartMs    int64
	EndMs      int64
}