Expand description
ML-powered error classification oracle for bashrs.
Uses aprender Random Forest classifier (GPU-accelerated via trueno/wgpu) to:
- Classify shell errors into actionable categories (24 categories)
- Suggest fixes based on error patterns
- Detect error drift requiring model retraining
§GPU Acceleration
Enable GPU feature for RTX 4090 acceleration via wgpu/trueno:
bashrs-oracle = { version = "*", features = ["gpu"] }§Performance Targets (from depyler-oracle)
- Accuracy: >90% (depyler achieved 97.73%)
- Training time: <1s
- Predictions/sec: >1000
- Model size: <1MB (with zstd compression)
Re-exports§
pub use categories::ErrorCategory;pub use classifier::ErrorClassifier;pub use corpus::Corpus;pub use corpus::TrainingExample;pub use features::ErrorFeatures;
Modules§
- categories
- Shell error categories for ML classification.
- classifier
- Keyword-based error classifier (fallback when ML model not trained).
- corpus
- Training corpus management for ML model.
- features
- Feature extraction for ML model.
Structs§
- Classification
Result - Classification result with confidence and suggested fix.
- Oracle
- ML-powered shell error classification oracle.
- Oracle
Config - Configuration for the Random Forest classifier.
Enums§
- Oracle
Error - Error types for the oracle.
Type Aliases§
- Result
- Result type for oracle operations.