"""
Preload all models into HuggingFace Hub cache at Docker build time.
This avoids cold-start downloads on the first request in production.
"""
from transformers import (
    AutoFeatureExtractor,
    AutoModelForAudioClassification,
    AutoModelForSequenceClassification,
    AutoModelForImageClassification,
    AutoTokenizer,
)

import sys

MODEL_GROUPS = {
    "Audio": [
        ("AutoFeatureExtractor", "MelodyMachine/Deepfake-audio-detection-V2"),
        ("AutoModelForAudioClassification", "MelodyMachine/Deepfake-audio-detection-V2"),
    ],
    "Text": [
        ("AutoTokenizer", "fakespot-ai/roberta-base-ai-text-detection-v1"),
        ("AutoModelForSequenceClassification", "fakespot-ai/roberta-base-ai-text-detection-v1"),
        ("AutoTokenizer", "Hello-SimpleAI/chatgpt-detector-roberta"),
        ("AutoModelForSequenceClassification", "Hello-SimpleAI/chatgpt-detector-roberta"),
        ("AutoTokenizer", "vikram71198/distilroberta-base-finetuned-fake-news-detection"),
        ("AutoModelForSequenceClassification", "vikram71198/distilroberta-base-finetuned-fake-news-detection"),
        ("AutoTokenizer", "jy46604790/Fake-News-Bert-Detect"),
        ("AutoModelForSequenceClassification", "jy46604790/Fake-News-Bert-Detect"),
    ],
    "Image": [
        ("AutoModelForImageClassification", "Ateeqq/ai-vs-human-image-detector"),
        ("AutoModelForImageClassification", "prithivMLmods/AI-vs-Deepfake-vs-Real"),
        ("AutoModelForImageClassification", "prithivMLmods/Deep-Fake-Detector-Model"),
    ],
}

LOADERS = {
    "AutoFeatureExtractor": AutoFeatureExtractor,
    "AutoModelForAudioClassification": AutoModelForAudioClassification,
    "AutoModelForSequenceClassification": AutoModelForSequenceClassification,
    "AutoModelForImageClassification": AutoModelForImageClassification,
    "AutoTokenizer": AutoTokenizer,
}

errors = []
for group, models in MODEL_GROUPS.items():
    print(f"\n── {group} ──")
    for loader_name, model_name in models:
        try:
            print(f"  Downloading {model_name} ({loader_name})...", end=" ", flush=True)
            LOADERS[loader_name].from_pretrained(model_name)
            print("OK")
        except Exception as e:
            print(f"FAILED: {e}")
            errors.append((model_name, str(e)))

if errors:
    print(f"\n⚠️  {len(errors)} model(s) failed to preload (will download on first request):")
    for name, err in errors:
        print(f"  - {name}: {err}")
else:
    print("\nAll models preloaded successfully.")