cleanup(fflag): delete dead enable_quality_filtering + enable_augmentation — [FFLAG-018a]

Both flags in unified_data_loader.rs config structs were declared and
defaulted but never read anywhere workspace-wide:
- DataProcessingConfig.enable_quality_filtering: set true, zero readers
- TrainingDataConfig.enable_augmentation: set false, zero readers

Deleted field + default at each of 2 sites. use_unified_extractor left
alone — it actively gates Option<UnifiedFeatureExtractor> at line 360.

crates/ml/src/training/unified_data_loader.rs

@@ -88,8 +88,6 @@ pub struct DataProcessingConfig {
     pub window_overlap_seconds: u64,
     /// Maximum data age to include (hours)
     pub max_age_hours: u64,
-    /// Enable data quality filtering
-    pub enable_quality_filtering: bool,
     /// Minimum data completeness ratio (0.0 to 1.0)
     pub min_completeness_ratio: f64,
 }
@@ -107,8 +105,6 @@ pub struct TrainingDataConfig {
     pub batch_size: usize,
     /// Maximum samples per symbol
     pub max_samples_per_symbol: Option<usize>,
-    /// Enable data augmentation
-    pub enable_augmentation: bool,
 }
 
 /// Feature extraction settings
@@ -326,7 +322,6 @@ impl Default for UnifiedDataLoaderConfig {
                 window_size_seconds: 60,
                 window_overlap_seconds: 30,
                 max_age_hours: 24,
-                enable_quality_filtering: true,
                 min_completeness_ratio: 0.8,
             },
             training: TrainingDataConfig {
@@ -335,7 +330,6 @@ impl Default for UnifiedDataLoaderConfig {
                 prediction_horizon: 1,
                 batch_size: 32,
                 max_samples_per_symbol: Some(10000),
-                enable_augmentation: false,
             },
             feature_extraction: FeatureExtractionSettings {
                 use_unified_extractor: true,