feat(ml-engine): Train Heuristic Regression Engine for Gas Cost Anomaly Detection

[SharifIbrahimDev]

Closes #606

Summary of Changes

• Implemented FeatureExtractor (libs/ml-engine/src/feature-extractor.ts) to extract structural AST metrics (cyclomatic complexity, max loop depth, variable count, storage accesses, memory allocations).
• Implemented GasPredictor (libs/ml-engine/src/predictor.ts) featuring heuristic regression model weights to compute a GasComplexityIndex.
• Added baseline comparison against industry averages (25.0 baseline score) and automated anomaly detection for code exceeding 50% baseline deviation.
• Provides optimization recommendations for high-complexity functions.
• Added comprehensive unit test coverage in libs/ml-engine/src/predictor.spec.ts.

Files Added

• libs/ml-engine/src/feature-extractor.ts
• libs/ml-engine/src/predictor.ts
• libs/ml-engine/src/index.ts
• libs/ml-engine/src/predictor.spec.ts

Acceptance Criteria Checklist

• Successfully outputs complexity index scores for submitted source code.
• Flags high-complexity functions lacking explicit static rule matches.
• All 6 unit tests passing.

[drips-wave]

@SharifIbrahimDev Great news! 🎉 Based on an automated assessment of this PR, the linked Wave issue(s) no longer count against your application limits.

You can now already apply to more issues while waiting for a review of this PR. Keep up the great work! 🚀

Learn more about application limits