redsl 1.1.0

ReDSL — Refactor + DSL + Self-Learning. LLM-powered autonomous code refactoring.

ReDSL

Refactor + DSL + Self-Learning — autonomous code refactoring with LLM, memory, and DSL.

ReDSL is a code refactoring system that combines static analysis, DSL rules, and LLM intelligence to automatically improve Python code quality.

Features

• 🔍 Static Analysis - Integration with popular linters and metrics tools
• 🧠 LLM with Reflection - Generate refactoring proposals with self-reflection loop
• ⚡ Hybrid Engine - Direct refactorings for simple changes, LLM for complex ones
• 📊 DSL Engine - Define refactoring rules in readable YAML format
• 💾 Memory System - Learn from refactoring history
• 🚀 Scalability - Process multiple projects simultaneously

Installation

pip install redsl

Quick Start

Basic CLI Usage

# Refactor a single project
redsl refactor ./my-project --max-actions 5 --dry-run

# Refactor without dry run
redsl refactor ./my-project --max-actions 10

Batch Processing

# Process semcod projects with LLM
redsl batch semcod /path/to/semcod --max-actions 10

# Hybrid refactoring (no LLM) for semcod projects
redsl batch hybrid /path/to/semcod --max-changes 30

Debugging

# Check configuration
redsl debug config --show-env

# View DSL decisions for a project
redsl debug decisions ./my-project --limit 20

Available Refactoring Actions

Simple Actions (no LLM)

• REMOVE_UNUSED_IMPORTS - Remove unused imports
• FIX_MODULE_EXECUTION_BLOCK - Fix module execution blocks
• EXTRACT_CONSTANTS - Extract magic numbers to constants
• ADD_RETURN_TYPES - Add return type annotations

Complex Actions (with LLM)

• EXTRACT_FUNCTIONS - Extract high-complexity functions
• SPLIT_MODULE - Split large modules
• REDUCE_COMPLEXITY - Reduce cyclomatic complexity

Architecture

┌─────────────────────────────────────────────────────┐
│                  ORCHESTRATOR                       │
│   (loop: analyze → decide → refactor → reflect)    │
├─────────────┬──────────────┬────────────────────────┤
│  ANALYZER   │  DSL ENGINE  │   REFACTOR ENGINE      │
│  ─ toon.yaml│  ─ rules     │   ─ patch generation   │
│  ─ linters  │  ─ scoring   │   ─ validation         │
│  ─ metrics  │  ─ planning  │   ─ application        │
├─────────────┴──────────────┴────────────────────────┤
│            HYBRID REFACTOR ENGINES                  │
│  ─ DirectRefactorEngine (no LLM)                   │
│  ─ LLM RefactorEngine (with reflection)            │
├─────────────────────────────────────────────────────┤
│                  LLM LAYER (LiteLLM)                │
│   ─ code generation  ─ reflection  ─ self-critique  │
├─────────────────────────────────────────────────────┤
│                 MEMORY SYSTEM                       │
│   ─ episodic (refactoring history)                 │
│   ─ semantic (patterns, rules)                     │
│   ─ procedural (strategies, plans)                 │
└─────────────────────────────────────────────────────┘

Configuration

Environment variables:

• OPENAI_API_KEY or OPENROUTER_API_KEY — API key
• REFACTOR_LLM_MODEL — LLM model (e.g., openrouter/openai/gpt-5.4-mini)
• REFACTOR_DRY_RUN — test mode (true/false)

Examples

Directory	Description
examples/01-basic-analysis/	Project analysis from toon.yaml files
examples/02-custom-rules/	Define custom DSL rules
examples/03-full-pipeline/	Full cycle: analyze → decide → refactor → reflect
examples/04-memory-learning/	Memory system: episodic, semantic, procedural

License

Apache License 2.0