// Data model shared by the server and the browser UI.

export type TrackKind = 'screen' | 'camera';

export interface Take {
  id: string;
  createdAt: string;
  status: 'recording' | 'processing' | 'ready' | 'failed';
  tracks: { screen: boolean; camera: boolean };
  // Which track file carries the microphone audio (null if no mic was recorded).
  audio: TrackKind | null;
  // Computer audio (what the speakers played), in system.webm, aligned with the other tracks.
  systemAudio?: boolean;
  // Seconds; 0 until the take is finalized.
  duration: number;
  transcript?: { status: 'pending' | 'done' | 'failed'; error?: string; updatedAt: string };
  // Background removal of the camera track (cutout.webm, VP9 with alpha). queued/running are live
  // states reported by the server; only done/failed/cancelled are persisted. While running, `stage`
  // says what is happening and `progress` (absent when unknown) is the fraction of that stage done.
  // `height` is the number
  // of lines the cutout was processed at, and `capped` says whether that was limited by the
  // processing resolution setting rather than by the camera (both absent for older cutouts).
  matte?: { status: 'queued' | 'running' | 'done' | 'failed' | 'cancelled'; stage?: string; progress?: number; error?: string; height?: number; capped?: boolean; updatedAt: string };
  // Pixel size of the screen track, as recorded (absent for takes from before it was stored).
  screenSize?: { width: number; height: number };
  error?: string;
}

// A piece of a take, [start, end) in take time (seconds). The timeline is an ordered list of these.
export interface Segment {
  id: string;
  takeId: string;
  start: number;
  end: number;
}

export type LayoutMode = 'pip' | 'side-by-side' | 'screen-only' | 'camera-only';
export type Corner = 'tl' | 'tr' | 'bl' | 'br';
export type CameraShape = 'rect' | 'rounded' | 'circle';
export type BackgroundMode = 'none' | 'blur' | 'color' | 'cutout';

// What replaces the room behind the speaker (requires background removal of the camera takes).
export interface Background {
  mode: BackgroundMode;
  color: string; // #rrggbb, for 'color'
  blur: number; // Gaussian sigma in pixels at 1080p output, for 'blur'
  // Background removal runs on the camera scaled down to at most this many lines. A small
  // picture-in-picture needs far fewer lines than the camera records, and the processing time is
  // roughly proportional to the number of pixels.
  resolution: MatteResolution;
}

export const MATTE_RESOLUTIONS = [180, 240, 360, 480, 720, 1080] as const;
export type MatteResolution = (typeof MATTE_RESOLUTIONS)[number];

export const DEFAULT_BACKGROUND: Background = { mode: 'none', color: '#1e2530', blur: 18, resolution: 480 };

// A cutout processed at fewer lines than the current setting asks for (and fewer than the camera has).
export const matteBelowSetting = (m: Take['matte'], bg: Background) => m?.status === 'done' && !!m.capped && (m.height ?? 0) < bg.resolution - 2;

export const backgroundOf = (l: Layout): Background => ({ ...DEFAULT_BACKGROUND, ...l.background });

// How screen and camera are combined in takes that have both.
export interface Layout {
  mode: LayoutMode;
  corner: Corner; // PiP corner; for side-by-side, the left/right side of the camera column
  size: number; // PiP width as a fraction of the output width
  shape: CameraShape;
  background?: Background; // absent in videos created before background removal existed
}

// A crop rectangle as fractions of the source frame, so it does not depend on the recorded resolution.
export interface Crop {
  x: number;
  y: number;
  w: number;
  h: number;
}

// Per-take crops of the raw tracks; a missing track means the full frame.
export type TakeCrop = Partial<Record<TrackKind, Crop>>;

export const cropOf = (v: Pick<Video, 'crops'>, takeId: string, track: TrackKind): Crop | undefined => v.crops?.[takeId]?.[track];

export const isFullFrame = (c: Crop) => c.x < 0.001 && c.y < 0.001 && c.w > 0.999 && c.h > 0.999;

// Export heights; the width is always 16:9. 1440p and 2160p show a high-resolution screen
// recording without scaling it down, at the cost of slower exports and larger files.
export const OUTPUT_HEIGHTS = [720, 1080, 1440, 2160] as const;
export type OutputHeight = (typeof OUTPUT_HEIGHTS)[number];
export const isOutputHeight = (h: unknown): h is OutputHeight => OUTPUT_HEIGHTS.includes(h as OutputHeight);

export interface OutputSettings {
  height: OutputHeight;
  normalizeAudio: boolean;
  systemVolume?: number; // gain applied to computer audio in the mix, 0..1 (default 1)
}

export const systemVolumeOf = (o: OutputSettings) => o.systemVolume ?? 1;

export interface ExportInfo {
  file: string;
  exportedAt: string;
  signature: string; // exportSignature() at the time of export, used to detect stale exports
  duration: number;
  bytes: number;
}

export interface Video {
  id: string;
  title: string;
  description: string;
  notes: string;
  createdAt: string;
  updatedAt: string;
  takes: Take[];
  timeline: Segment[];
  layout: Layout;
  crops?: Record<string, TakeCrop>; // by take id; absent in videos created before cropping existed
  output: OutputSettings;
  thumbnail: { file: string; custom: boolean; updatedAt: string } | null;
  export: ExportInfo | null;
}

export interface VideoSummary {
  id: string;
  title: string;
  description: string;
  createdAt: string;
  updatedAt: string;
  duration: number;
  takeCount: number;
  hasScreen: boolean;
  hasCamera: boolean;
  thumbnailUrl: string | null;
  exportState: 'none' | 'current' | 'stale';
}

export interface ExportJob {
  status: 'running' | 'done' | 'failed';
  progress: number; // 0..1
  startedAt: string;
  error?: string;
}

export interface AppConfig {
  deepgramModel: string;
  autoTranscribe: boolean;
  defaultCountdown: number;
  defaultCameraHeight: 720 | 1080;
  defaultOutputHeight: OutputHeight;
  matteHost: string; // ssh destination for background removal on a GPU; empty for this computer
  matteSetup: string; // shell commands run on that host first, e.g. "module load python ffmpeg"
}

export interface PublicConfig extends AppConfig {
  hasDeepgramKey: boolean;
  libraryDir: string;
}

export interface Word {
  word: string;
  text: string; // punctuated form for display
  start: number;
  end: number;
}

export interface Transcript {
  takeId: string;
  model: string;
  createdAt: string;
  text: string;
  words: Word[];
}

// Audio peaks for waveform display: `rate` values per second, each 0..255, base64-encoded bytes.
export interface Peaks {
  rate: number;
  data: string;
}

export function exportSignature(v: Pick<Video, 'timeline' | 'layout' | 'output' | 'crops' | 'takes'>): string {
  const seg = v.timeline.map((s) => [s.takeId, round3(s.start), round3(s.end)]);
  const l = v.layout;
  const o = v.output;
  const b = backgroundOf(l);
  // The background is omitted when off so that exports made before it existed stay current.
  const bg = b.mode === 'color' ? ['color', b.color] : b.mode === 'blur' ? ['blur', b.blur] : b.mode;
  // Likewise, crops are included only for takes in the timeline that have one.
  const crop: Record<string, (number[] | null)[]> = {};
  for (const id of new Set(v.timeline.map((s) => s.takeId))) {
    const c = v.crops?.[id];
    const r = (x?: Crop) => (x ? [round3(x.x), round3(x.y), round3(x.w), round3(x.h)] : null);
    if (c?.screen || c?.camera) crop[id] = [r(c.screen), r(c.camera)];
  }
  return JSON.stringify({
    seg,
    layout: [l.mode, l.corner, round3(l.size), l.shape],
    ...(b.mode === 'none' ? {} : { bg }),
    ...(Object.keys(crop).length ? { crop } : {}),
    // And the computer audio level only matters when a take in the timeline has computer audio.
    ...(v.timeline.some((s) => v.takes.find((t) => t.id === s.takeId)?.systemAudio) ? { sys: round3(systemVolumeOf(o)) } : {}),
    output: [o.height, o.normalizeAudio],
  });
}

function round3(x: number) {
  return Math.round(x * 1000) / 1000;
}

// Input gain of a microphone (see server/micgain.ts).
export interface MicGain {
  available: boolean; // false without wpctl, or when the microphone is not a PipeWire source
  reason?: string;
  node?: string; // wpctl target: a node id, or @DEFAULT_AUDIO_SOURCE@
  description?: string;
  volume?: number; // wpctl scale: 1.0 = 100%; a factor k is about 60·log10(k) dB
  muted?: boolean;
}

export const MAX_MIC_GAIN = 1.5;