import type { AiConfig } from "../factory";
import { recognizePhoto } from "./recognize-photo";
import { generateRecipeFromRecognition, type GeneratedRecipeFromRecognition } from "./generate-recipe-from-recognition";

export type ImportedRecipe =
  | { found: false; recipeType: "dish" | "drink"; title: string; ingredients: []; steps: [] }
  | ({ found: true; recipeType: "dish" | "drink" } & GeneratedRecipeFromRecognition);

/** Orchestrates the two-step photo-import flow: a vision model recognizes
 * what's in the photo (`recognizePhoto`), then a text model reconstructs the
 * full structured recipe from that recognition (`generateRecipeFromRecognition`).
 * Splitting the call lets each step use the model best suited to it — vision
 * for the photo, text for structuring — instead of one model doing both. */
export async function importFromPhoto(
  imageBase64: string,
  mimeType: "image/jpeg" | "image/png" | "image/webp",
  visionConfig: AiConfig | undefined,
  textConfig: AiConfig | undefined,
  locale?: string,
): Promise<ImportedRecipe> {
  const recognition = await recognizePhoto(imageBase64, mimeType, visionConfig);

  if (!recognition.found) {
    return { found: false, recipeType: recognition.recipeType, title: recognition.title, ingredients: [], steps: [] };
  }

  const generated = await generateRecipeFromRecognition(recognition, { ...textConfig, language: locale ?? "en" });

  return { found: true, recipeType: recognition.recipeType, ...generated };
}