dailyou/lib/core/llm/model_download_service.dart

import 'dart:io';
import 'package:path_provider/path_provider.dart';
import 'package:path/path.dart' as p;

class ModelDownloadService {
  static const modelFileName = 'gemma-2b-it-gpu-int4.bin';
  static const modelSizeBytes = 1183285248; // ~1.1 GB

  // Gemma 2B IT CPU int4 — MediaPipe LLM Inference model
  static const _downloadUrl =
      'https://storage.googleapis.com/mediapipe-models/llm_inference/'
      'gemma-2b-it-cpu-int4/float32/1/gemma-2b-it-cpu-int4.bin';

  Future<String> get modelPath async {
    final dir = await getApplicationSupportDirectory();
    return p.join(dir.path, modelFileName);
  }

  Future<bool> isModelPresent() async {
    final path = await modelPath;
    final file = File(path);
    if (!file.existsSync()) return false;
    // Verify the file isn't a partial download (allow small variance)
    final size = await file.length();
    return size > modelSizeBytes * 0.99;
  }

  /// Streams download progress as a value from 0.0 to 1.0.
  Stream<double> download() async* {
    final path = await modelPath;
    final file = File(path);
    final client = HttpClient();

    try {
      final request = await client.getUrl(Uri.parse(_downloadUrl));
      final response = await request.close();

      if (response.statusCode != 200) {
        throw Exception('Download failed: HTTP ${response.statusCode}');
      }

      final totalBytes =
          response.contentLength > 0 ? response.contentLength : modelSizeBytes;
      int receivedBytes = 0;

      final sink = file.openWrite();
      try {
        await for (final chunk in response) {
          sink.add(chunk);
          receivedBytes += chunk.length;
          yield (receivedBytes / totalBytes).clamp(0.0, 1.0);
        }
      } finally {
        await sink.close();
      }
    } catch (_) {
      if (await file.exists()) await file.delete();
      rethrow;
    } finally {
      client.close();
    }
  }
}