v3.2.2 Sandbox Security and Code Interpreter Architecture

Full Changelog: v3.2.2...v3.3.0

VERSION v3.3.0 (Summary of Key Changes)

This update mainly improves security, stability, and how code runs in a controlled environment.

MAIN FEATURE: SANDBOX MODE

• A new sandbox system is now the default way code runs
• You can control it using:
  • /sandbox → safe execution
  • /unsafe → less restricted execution
• The old --unsafe flag is replaced with --sandbox / --no-sandbox
• Sandbox now has stronger protection against harmful commands and file access

SECURITY IMPROVEMENTS

• Better blocking of dangerous system-level commands
• Fixed ways users could bypass safety (file writes, absolute paths, symlinks)
• Added stricter checks for file operations like .write()
• Improved detection of unsafe patterns across Python and other scripts
• Safer subprocess handling and execution delegation

EXECUTION & PERFORMANCE

• Increased timeout limit in safe mode to 300 seconds for long-running code
• Improved handling of stuck or long processes using process group kill
• Better detection of Python code using AST parsing
• Fixed watchdog timer issues in sandbox

STABILITY & BUG FIXES

• Fixed syntax errors and test failures
• Cleaned up execution logic formatting
• Fixed temporary file execution issues
• Resolved multiple high-priority (P0/P1/P2) security bugs

BUILD & TOOLING

• Improved build_release.sh script with:
  • better error handling
  • cleaner structure
  • more reliable release process

Overall, this release focuses on making the interpreter safer, more reliable, and better at handling real-world code execution, especially with the new sandbox-first approach.

v3.2.1

What's Changed

• Enhance model catalog, execution safety, and TUI features by @haseeb-heaven in #24
• Update model configs to newer LLM releases and fix routing issues by @haseeb-heaven in #23

Full Changelog: v3.1.0...v3.2.1

Code Interpreter v3.1.0

Interpreter 3.1.0 Latest

@haseeb-heaven haseeb-heaven released this Apr 5, 2026

3.1.0

Release highlights:

• Added OpenRouter support with paid and free model aliases, including openrouter/free as the default OpenRouter selection.
• Improved the safe execution sandbox with bounded repair retries and cleaner recovery from provider errors.
• Fixed prompt-intent drift so simple tasks generate simple executable code.
• Added refreshed TUI screenshots and usage documentation.

Changelog:

• v3.1.0 - Added OpenRouter support and free model aliases, improved simple-task code generation, raised repair attempts to 3, and refreshed release docs/screenshots.
• v3.0.0 - Added execution sandbox, circuit breaker, bounded ReACT-style repair retries, and polished CLI/TUI runtime output.
• v2.4.1 - Added NVIDIA, Z AI, Browser Use, .env.example, and --cli / --tui flows.

Assets:

• interpreter.zip
• Source code (zip)
• Source code (tar.gz)

Interpreter 2.1

🔥 v2.0 - Added Groq-AI Models Fastest LLM with 500 Tokens/Sec with Code-LLaMa, Mixtral models.

• v2.0.1 - Added AnthropicAI Claude-2, Instant models.

🔥 v2.1 - Added AnhtorpicAI Claude-3 models powerful Opus,Sonnet,Haiku models.

Interpreter 1.8

🌴 v1.8

Interpreter added commands 🖥️

• 🚪 /exit - Exit the interpreter.
• ▶️ /execute - Execute the last code generated.
• 📦 /install - Install a package from npm or pip.
• 🔄 /mode - Change the mode of interpreter.
• 🔄 /model - Change the model for interpreter.
• 🌐 /language - Change the language of the interpreter.
• 🧹 /clear - Clear the screen.
• 🆘 /help - Display this help message.
• 📝 /version - Display the version of the interpreter.

Interpreter 1.7

Changelog

• 🌴 v1.7
  • Added Gemini Pro Vision support for Image Processing. 🖼️
  • Introduced Google Gemini models support with Gemini Pro and Gemini Pro Vision for image analysis. 🧠
  • This update is a significant improvement over Hugging Face models because:
    • It's free. 💸
    • Offers a 60 RPM (requests per minute) limit, which is better than any other free tier models available. 💡

Interpreter 1.6

📝 v1.6 - Updated Code Interpreter for Document files (JSON, CSV, XML)

Features:

• 📂 Multi-format Support: Supports JSON, CSV, and XML files.
• 🔄 File Parsing: Efficiently parses chosen document files.
• 📄 JSON Processing:
  • 🧩 JSON Parsing: Parses JSON documents.
  • 📑 JSON to Python: Converts JSON to Python data structures.
• 📊 CSV Processing:
  • 📎 CSV Parsing: Parses CSV files.
  • 📊 Data Analysis: Analyzes CSV data.
• 📃 XML Processing:
  • 🌐 XML Parsing: Parses XML documents.
  • 🧱 XML to Python: Converts XML to Python objects.
• 🛠️ Modular Design: Organized into modules for scalability.
• ❗ Error Handling: Comprehensive error handling.
• 📝 Logging: Includes logging for debugging.
• 💬 Comments: Detailed code comments.
• 🚀 Efficiency: Optimized for speed and memory.
• 🧩 Full Source Code: No omissions in code.
• 🚦 Exception Handling: Robust exception handling.