feat(iOS): 更新MNN后端模型配置优化性能

将MNN主模型从Qwen3.5-4B(~2.64GiB)降级为Qwen3.5-2B(~1.1GiB),因为4B版本
实测运行过慢,影响用户体验。iPhone17+/SME2设备使用2B模型,保留MLX
兜底方案用于模拟器和备用场景,确保AI推理性能和存储效率的平衡。
```
This commit is contained in:
link2026
2026-06-09 22:20:07 +08:00
parent ca5a3fa38b
commit b79ae54b7b
40 changed files with 1327 additions and 452 deletions

View File

@@ -74,8 +74,8 @@ struct DiaryAssistService {
// 1. <think>...</think>( HealthExportService )
let stripped = HealthExportService.stripThinkBlocks(collected)
// 2. JSON( CaptureService.extractJSONObject)
let jsonStr = CaptureService.extractJSONObject(from: stripped)
// 2. JSON( CaptureService.extractJSONObject)+
let jsonStr = CaptureService.repairJSON(CaptureService.extractJSONObject(from: stripped))
guard let data = jsonStr.data(using: .utf8),
let obj = try? JSONSerialization.jsonObject(with: data, options: [.fragmentsAllowed]),
let dict = obj as? [String: Any] else {