evOo-local/apps/web/src/components/media/MediaCard.tsx

import { useLingui } from "@lingui/react/macro";
import type {
  MediaJobBlock,
  MediaJobStatus,
  MediaOperation,
  MediaOutput,
  MediaPresetId,
} from "@rakazo/contracts";
import { MEDIA_JOB_ACTIVE_STATUSES, MEDIA_PRESETS, MediaPresetIdSchema } from "@rakazo/contracts";
import {
  Button,
  buttonVariants,
  cn,
  DropdownMenu,
  DropdownMenuContent,
  DropdownMenuItem,
  DropdownMenuTrigger,
} from "@rakazo/ui-web";
import type { LucideIcon } from "lucide-react";
import {
  Captions,
  ChevronDown,
  Download,
  Film,
  ImageIcon,
  ScanSearch,
  Scissors,
  Sparkles,
} from "lucide-react";
import { useEffect, useId, useState } from "react";
import type { ArtifactTarget } from "../../lib/artifact-open";
import { artifactUrl } from "../../lib/artifact-url";
import { rpc } from "../../lib/rpc";
import { ArtifactImage } from "../../pages/shell/message-cards";
import { ArtifactFileCard } from "../ArtifactFileCard";
import { Shimmer } from "../ai/primitives";
import { MediaPlayer } from "./MediaPlayer";

const CARD_CLASS =
  "w-[min(480px,96%)] rounded-[18px] border border-border bg-card/75 p-3.5 text-start shadow-xs";

export type MediaCardAction =
  | { kind: "export"; artifactId: string; preset: MediaPresetId }
  | { kind: "transcribe"; artifactId: string; name: string }
  | { kind: "cancel" };

/** Which follow-up jobs the space can run; actions it cannot run are not offered. */
export interface MediaCardAvailability {
  export: boolean;
  transcribe: boolean;
}

const NOTHING_AVAILABLE: MediaCardAvailability = { export: false, transcribe: false };

const OPERATION_ICONS: Record<MediaOperation, LucideIcon> = {
  generate_image: Sparkles,
  generate_video: Sparkles,
  edit_image: ImageIcon,
  edit_video: Scissors,
  export_video: Film,
  transcribe: Captions,
  analyze_video: ScanSearch,
};

export function isActiveMediaStatus(status: MediaJobStatus): boolean {
  return (MEDIA_JOB_ACTIVE_STATUSES as readonly MediaJobStatus[]).includes(status);
}

/** Formats a video can be exported to: every preset except the shape it already has. */
export function exportPresetsFor(output: Pick<MediaOutput, "width" | "height" | "preset">) {
  const ratio = output.width && output.height ? output.width / output.height : null;
  return MediaPresetIdSchema.options.filter((id) => {
    if (id === output.preset) return false;
    const preset = MEDIA_PRESETS[id];
    return ratio === null || Math.abs(preset.width / preset.height - ratio) > 0.01;
  });
}

function StatusLabel({ status }: { status: MediaJobStatus }) {
  const { t } = useLingui();
  if (status === "running") {
    return (
      <span className="text-ui-body-sm font-medium">
        <Shimmer>{t`Working…`}</Shimmer>
      </span>
    );
  }
  const label =
    status === "queued"
      ? t`Queued`
      : status === "waiting"
        ? t`Waiting for GPU`
        : status === "done"
          ? t`Done`
          : status === "failed"
            ? t`Failed`
            : t`Cancelled`;
  return (
    <span
      className={cn(
        "text-ui-body-sm font-medium",
        status === "done"
          ? "text-success"
          : status === "failed"
            ? "text-destructive"
            : "text-muted-foreground",
      )}
    >
      {label}
    </span>
  );
}

function OutputActions({
  output,
  available,
  busy,
  onAction,
}: {
  output: MediaOutput;
  available: MediaCardAvailability;
  busy: boolean;
  onAction?: (action: MediaCardAction) => void;
}) {
  const { t } = useLingui();
  const name = output.name;
  const presets = output.kind === "video" ? exportPresetsFor(output) : [];
  return (
    <div className="flex flex-wrap items-center gap-1.5">
      <a
        href={artifactUrl(output.artifactId, { download: true })}
        download={name}
        aria-label={t`Download ${name}`}
        title={t`Download ${name}`}
        className={cn(
          buttonVariants({ variant: "ghost", size: "icon-sm" }),
          "text-muted-foreground",
        )}
      >
        <Download />
      </a>
      {onAction && available.export && presets.length > 0 ? (
        <DropdownMenu>
          <DropdownMenuTrigger
            disabled={busy}
            render={<Button variant="outline" size="sm" data-testid="media-export" />}
          >
            <Film />
            {t`Export`}
            <ChevronDown />
          </DropdownMenuTrigger>
          <DropdownMenuContent className="w-auto min-w-24">
            {presets.map((preset) => (
              <DropdownMenuItem
                key={preset}
                onClick={() => onAction({ kind: "export", artifactId: output.artifactId, preset })}
              >
                {MEDIA_PRESETS[preset].aspect}
              </DropdownMenuItem>
            ))}
          </DropdownMenuContent>
        </DropdownMenu>
      ) : null}
      {onAction && available.transcribe && (output.kind === "video" || output.kind === "audio") ? (
        <Button
          variant="outline"
          size="sm"
          disabled={busy}
          onClick={() =>
            onAction({ kind: "transcribe", artifactId: output.artifactId, name: output.name })
          }
        >
          <Captions />
          {t`Transcribe`}
        </Button>
      ) : null}
    </div>
  );
}

/**
 * The live card of a media job: what it makes, how far it is, and the results with the
 * follow-ups that fit them (export other formats, transcribe). Nothing else is shown.
 */
export function MediaCardView({
  block,
  available = NOTHING_AVAILABLE,
  onAction,
}: {
  block: MediaJobBlock;
  available?: MediaCardAvailability;
  /** Starts a follow-up job or cancels this one; rejects with a message to show. */
  onAction?: (action: MediaCardAction) => Promise<void>;
}) {
  const { t } = useLingui();
  const titleId = useId();
  const [busy, setBusy] = useState(false);
  const [actionError, setActionError] = useState<string | null>(null);
  const active = isActiveMediaStatus(block.status);
  const Icon = OPERATION_ICONS[block.operation];
  const percent = Math.round((block.progress ?? 0) * 100);
  const images = block.outputs.filter((output) => output.kind === "image");
  const others = block.outputs.filter((output) => output.kind !== "image");

  const act = onAction
    ? (action: MediaCardAction) => {
        setBusy(true);
        setActionError(null);
        void onAction(action)
          .catch((error: unknown) =>
            setActionError(error instanceof Error && error.message ? error.message : t`Failed`),
          )
          .finally(() => setBusy(false));
      }
    : undefined;

  return (
    <div className="my-2 flex justify-start">
      <div data-testid="media-card" data-status={block.status} className={CARD_CLASS}>
        <div className="flex items-center justify-between gap-2">
          <span className="flex min-w-0 items-center gap-2.5">
            <Icon aria-hidden="true" className="size-icon-md shrink-0 text-muted-foreground" />
            <span
              id={titleId}
              className="truncate text-ui-body font-medium text-foreground"
              dir="auto"
              title={block.title}
            >
              {block.title}
            </span>
          </span>
          <span className="flex shrink-0 items-center gap-1.5">
            <StatusLabel status={block.status} />
            {active && act ? (
              <Button
                variant="ghost"
                size="xs"
                disabled={busy}
                onClick={() => act({ kind: "cancel" })}
              >
                {t`Cancel`}
              </Button>
            ) : null}
          </span>
        </div>
        {active ? (
          <div
            role="progressbar"
            aria-labelledby={titleId}
            aria-valuemin={0}
            aria-valuemax={100}
            aria-valuenow={block.progress === undefined ? undefined : percent}
            className="mt-2.5 h-1 overflow-hidden rounded-full bg-muted"
          >
            <div
              className={cn(
                "h-full rounded-full bg-primary transition-[width] duration-500",
                block.progress === undefined && "w-1/3 animate-pulse",
              )}
              style={block.progress === undefined ? undefined : { width: `${percent}%` }}
            />
          </div>
        ) : null}
        {block.status === "failed" && block.error ? (
          <p className="mt-2 text-ui-body-sm text-destructive" dir="auto">
            {block.error}
          </p>
        ) : null}
        {images.length > 0 ? (
          <div className="mt-3 flex flex-wrap gap-2">
            {images.map((output) => (
              <ArtifactImage
                key={output.artifactId}
                artifactId={output.artifactId}
                name={output.name}
              />
            ))}
          </div>
        ) : null}
        {others.map((output) => (
          <div key={output.artifactId} className="mt-3 flex flex-col gap-1.5">
            {output.kind === "video" || output.kind === "audio" ? (
              <>
                <MediaPlayer
                  artifactId={output.artifactId}
                  kind={output.kind}
                  name={output.name}
                  posterArtifactId={output.posterArtifactId}
                  width={output.width}
                  height={output.height}
                />
                {active ? null : (
                  <OutputActions output={output} available={available} busy={busy} onAction={act} />
                )}
              </>
            ) : (
              <ArtifactFileCard
                artifactId={output.artifactId}
                name={output.name}
                mimeType={output.mimeType}
                size={output.size}
              />
            )}
          </div>
        ))}
        {actionError ? (
          <p role="alert" className="mt-2 text-ui-body-sm text-destructive" dir="auto">
            {actionError}
          </p>
        ) : null}
      </div>
    </div>
  );
}

const CAPABILITIES_TTL_MS = 60_000;
let capabilities:
  | { conversation: string; at: number; value: Promise<MediaCardAvailability> }
  | undefined;

/**
 * What the card's space can run, shared by every card of the conversation on screen and
 * refreshed after a minute. Asked through a job, since the main conversation can live in another
 * space than the one selected.
 */
function loadAvailability(target: ArtifactTarget, jobId: string): Promise<MediaCardAvailability> {
  const conversation = "botId" in target ? `bot:${target.botId}` : `group:${target.groupId}`;
  if (
    !capabilities ||
    capabilities.conversation !== conversation ||
    Date.now() - capabilities.at > CAPABILITIES_TTL_MS
  ) {
    capabilities = {
      conversation,
      at: Date.now(),
      value: rpc.media
        .capabilities({ jobId })
        .then((value) => ({
          export: value.export_video === true,
          transcribe: value.transcribe === true,
        }))
        .catch(() => NOTHING_AVAILABLE),
    };
  }
  return capabilities.value;
}

function useAvailability(
  enabled: boolean,
  target: ArtifactTarget,
  jobId: string,
): MediaCardAvailability {
  const [available, setAvailable] = useState(NOTHING_AVAILABLE);
  useEffect(() => {
    if (!enabled) return;
    let current = true;
    void loadAvailability(target, jobId).then((value) => {
      if (current) setAvailable(value);
    });
    return () => {
      current = false;
    };
  }, [enabled, target, jobId]);
  return available;
}

/** The media card in a conversation, with its follow-up actions wired to the media job RPCs. */
export function MediaCard({
  block,
  target,
  messageId,
}: {
  block: MediaJobBlock;
  target: ArtifactTarget;
  /** The message carrying the card; a follow-up job is posted by the same bot. */
  messageId: string;
}) {
  // Follow-ups apply to video and audio of a settled job only; other cards never ask.
  const available = useAvailability(
    !isActiveMediaStatus(block.status) &&
      block.outputs.some((output) => output.kind === "video" || output.kind === "audio"),
    target,
    block.jobId,
  );
  const onAction = async (action: MediaCardAction) => {
    if (action.kind === "cancel") {
      await rpc.media.jobs.cancel({ jobId: block.jobId });
      return;
    }
    await rpc.media.jobs.start({
      ...target,
      messageId,
      ...(action.kind === "export"
        ? {
            operation: "export_video",
            input: { artifact_id: action.artifactId, presets: [action.preset] },
          }
        : // The new card is titled with the file it transcribes.
          {
            operation: "transcribe",
            input: { artifact_id: action.artifactId, title: action.name },
          }),
    });
  };
  return <MediaCardView block={block} available={available} onAction={onAction} />;
}