# nanawareatharva/codesentinel architecture

> Architecture diagram of the GitHub repository nanawareatharva/codesentinel, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-10-03). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/nanawareatharva/codesentinel
- Repository: https://github.com/nanawareatharva/codesentinel

## Overview

CodeSentinel’s implemented product is BugLens: it builds a defect-prediction model from labeled defect datasets, then analyzes a local Python repository to rank functions by risk and explain the highest-risk result. The README also describes AutoTestArmy and a feedback loop as future capabilities; their directories exist, but the sampled files do not implement them. Edges reflect sampled calls or explicit README statements; future-stage links are documented but not verified in source.

Main entry points: [`buglens/model/predict.py`](https://github.com/nanawareatharva/codesentinel/blob/main/buglens/model/predict.py) (Risk Prediction), [`buglens/config.py`](https://github.com/nanawareatharva/codesentinel/blob/main/buglens/config.py) (Feature Schema), [`buglens/model/train.py`](https://github.com/nanawareatharva/codesentinel/blob/main/buglens/model/train.py) (Model Training), [`scripts/build_feature_matrix.py`](https://github.com/nanawareatharva/codesentinel/blob/main/scripts/build_feature_matrix.py) (Feature Matrix)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_data["Training Data"]
  node_dataset_loader["Dataset Loader<br/>[dataset_loader.py]"]
  node_feature_matrix["Feature Matrix"]
  node_trainer["Model Training<br/>[train.py]"]
end

subgraph group_buglens["BugLens Analysis"]
  node_config["Feature Schema<br/>[config.py]"]
  node_artifacts[("Model Artifacts")]
  node_git_miner["Git History Mining<br/>[git_miner.py]"]
  node_metric_extractor["Function Metrics"]
  node_predictor["Risk Prediction<br/>[predict.py]"]
  node_risk_results["Ranked Risk Results<br/>[predict.py]"]
  node_explainer["SHAP Explanations<br/>[shap_explainer.py]"]
  node_demo["Demo Runner<br/>[demo_buglens.py]"]
end

subgraph group_future["Planned Capabilities"]
  node_autotestarmy["Targeted Test Generation"]
  node_feedback["Feedback Loop"]
end

node_dataset_sources[("NASA / PROMISE")]
node_developer(("Developer"))
node_repository["Python Repository"]

node_dataset_sources -->|"provides datasets"| node_dataset_loader
node_dataset_loader -->|"uses schema"| node_config
node_feature_matrix -->|"loads datasets"| node_dataset_loader
node_feature_matrix -->|"uses schema"| node_config
node_feature_matrix -->|"training data"| node_trainer
node_trainer -->|"uses schema"| node_config
node_trainer -->|"saves model"| node_artifacts
node_developer -->|"runs analysis"| node_demo
node_demo -->|"calls prediction"| node_predictor
node_repository -->|"analyzed by"| node_predictor
node_predictor -->|"mines history"| node_git_miner
node_predictor -->|"extracts metrics"| node_metric_extractor
node_predictor -->|"uses schema"| node_config
node_predictor -->|"loads model"| node_artifacts
node_predictor -->|"ranks functions"| node_risk_results
node_demo -->|"explains top risk"| node_explainer
node_explainer -->|"uses schema"| node_config
node_explainer -->|"loads explainer"| node_artifacts
node_risk_results -.->|"prioritizes tests"| node_autotestarmy
node_autotestarmy -.->|"test outcomes"| node_feedback
node_feedback -.->|"refines training"| node_trainer

click node_dataset_loader "https://github.com/nanawareatharva/codesentinel/blob/main/buglens/mining/dataset_loader.py"
click node_feature_matrix "https://github.com/nanawareatharva/codesentinel/blob/main/scripts/build_feature_matrix.py"
click node_config "https://github.com/nanawareatharva/codesentinel/blob/main/buglens/config.py"
click node_trainer "https://github.com/nanawareatharva/codesentinel/blob/main/buglens/model/train.py"
click node_git_miner "https://github.com/nanawareatharva/codesentinel/blob/main/buglens/mining/git_miner.py"
click node_metric_extractor "https://github.com/nanawareatharva/codesentinel/blob/main/buglens/mining/metric_extractor.py"
click node_predictor "https://github.com/nanawareatharva/codesentinel/blob/main/buglens/model/predict.py"
click node_risk_results "https://github.com/nanawareatharva/codesentinel/blob/main/buglens/model/predict.py"
click node_explainer "https://github.com/nanawareatharva/codesentinel/blob/main/buglens/model/shap_explainer.py"
click node_demo "https://github.com/nanawareatharva/codesentinel/blob/main/scripts/demo_buglens.py"
click node_autotestarmy "https://github.com/nanawareatharva/codesentinel/tree/main/autotestarmy"
click node_feedback "https://github.com/nanawareatharva/codesentinel/tree/main/feedback"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_dataset_loader,node_feature_matrix,node_trainer toneBlue
class node_config,node_artifacts,node_git_miner,node_metric_extractor,node_predictor,node_risk_results,node_explainer,node_demo,node_dataset_sources toneAmber
class node_autotestarmy,node_feedback toneMint
class node_developer,node_repository toneIndigo
```

## Components

### Training Data

- [Dataset Loader](https://github.com/nanawareatharva/codesentinel/blob/main/buglens/mining/dataset_loader.py): `buglens/mining/dataset_loader.py`
- [Feature Matrix](https://github.com/nanawareatharva/codesentinel/blob/main/scripts/build_feature_matrix.py): `scripts/build_feature_matrix.py`
- [Model Training](https://github.com/nanawareatharva/codesentinel/blob/main/buglens/model/train.py): `buglens/model/train.py`

### BugLens Analysis

- [Feature Schema](https://github.com/nanawareatharva/codesentinel/blob/main/buglens/config.py): `buglens/config.py`
- **Model Artifacts**
- [Git History Mining](https://github.com/nanawareatharva/codesentinel/blob/main/buglens/mining/git_miner.py): `buglens/mining/git_miner.py`
- [Function Metrics](https://github.com/nanawareatharva/codesentinel/blob/main/buglens/mining/metric_extractor.py): `buglens/mining/metric_extractor.py`
- [Risk Prediction](https://github.com/nanawareatharva/codesentinel/blob/main/buglens/model/predict.py): `buglens/model/predict.py`
- [Ranked Risk Results](https://github.com/nanawareatharva/codesentinel/blob/main/buglens/model/predict.py): `buglens/model/predict.py`
- [SHAP Explanations](https://github.com/nanawareatharva/codesentinel/blob/main/buglens/model/shap_explainer.py): `buglens/model/shap_explainer.py`
- [Demo Runner](https://github.com/nanawareatharva/codesentinel/blob/main/scripts/demo_buglens.py): `scripts/demo_buglens.py`

### Planned Capabilities

- [Targeted Test Generation](https://github.com/nanawareatharva/codesentinel/tree/main/autotestarmy): `autotestarmy`
- [Feedback Loop](https://github.com/nanawareatharva/codesentinel/tree/main/feedback): `feedback`

### Other components

- **NASA / PROMISE**
- **Developer**
- **Python Repository**

## Connections

- NASA / PROMISE → Dataset Loader: provides datasets (evidence: `README.md`)
- Dataset Loader → Feature Schema: uses schema (evidence: `buglens/mining/dataset_loader.py`)
- Feature Matrix → Dataset Loader: loads datasets (evidence: `scripts/build_feature_matrix.py`)
- Feature Matrix → Feature Schema: uses schema (evidence: `scripts/build_feature_matrix.py`)
- Feature Matrix → Model Training: training data (evidence: `README.md`)
- Model Training → Feature Schema: uses schema (evidence: `buglens/model/train.py`)
- Model Training → Model Artifacts: saves model (evidence: `buglens/model/train.py`)
- Developer → Demo Runner: runs analysis (evidence: `README.md`)
- Demo Runner → Risk Prediction: calls prediction (evidence: `scripts/demo_buglens.py`)
- Python Repository → Risk Prediction: analyzed by (evidence: `buglens/model/predict.py`)
- Risk Prediction → Git History Mining: mines history (evidence: `buglens/model/predict.py`)
- Risk Prediction → Function Metrics: extracts metrics (evidence: `buglens/model/predict.py`)
- Risk Prediction → Feature Schema: uses schema (evidence: `buglens/model/predict.py`)
- Risk Prediction → Model Artifacts: loads model (evidence: `buglens/model/predict.py`)
- Risk Prediction → Ranked Risk Results: ranks functions (evidence: `buglens/model/predict.py`)
- Demo Runner → SHAP Explanations: explains top risk (evidence: `scripts/demo_buglens.py`)
- SHAP Explanations → Feature Schema: uses schema (evidence: `buglens/model/shap_explainer.py`)
- SHAP Explanations → Model Artifacts: loads explainer (evidence: `buglens/model/shap_explainer.py`)
- Ranked Risk Results → Targeted Test Generation: prioritizes tests (evidence: `README.md`)
- Targeted Test Generation → Feedback Loop: test outcomes (evidence: `README.md`)
- Feedback Loop → Model Training: refines training (evidence: `README.md`)
