Skip to main content

What's New in Version 0.673.0

Released on March 11, 2026

This release brings powerful GraphQL support to API Tools, enhanced diff visualisation for versioning, native SDK integration in code interpreter, massively improved Plan Mode with multiple choice interactions, expanded creative capabilities for all plans, orchestrator benchmarking, and a refined voice cloning experience! 🚀

🌐 GraphQL Support in API Tools​

Native GraphQL Queries & Mutations​

API Tools now natively support GraphQL queries and mutations, bringing all the context-aware functionalities ToothFairyAI is known for to the GraphQL ecosystem.

Key Capabilities:

  • Full GraphQL Support - Execute queries and mutations with the same ease as REST API calls
  • JSON Path Extractor - Leverage our powerful JSON path extraction for precise data retrieval from GraphQL responses
  • Scope Management - Context-aware scoping that works seamlessly with GraphQL operations
  • Callback Integration - All callback functionalities are fully compatible with GraphQL endpoints
  • Unified Experience - Same intuitive interface whether you're working with REST or GraphQL APIs

This enhancement makes it effortless to integrate modern GraphQL services into your agent workflows while maintaining all the intelligent features you expect from ToothFairyAI.

📊 Enhanced Diff UI for Versioning​

Pinpoint Precision for Every Change​

We've significantly improved the diff UI when reviewing changes among different versions of Agents, Hooks, and Tools, giving you complete visibility into every modification.

Improvements:

  • Granular Change Detection - Identify every single change, no matter how small
  • Large String Handling - Pinpoint changes even within large text blocks and complex configurations
  • Side-by-Side Comparison - Clear visual representation of before and after states
  • Highlighted Differences - Colour-coded changes make it easy to spot modifications at a glance
  • Character-Level Precision - See exactly which characters changed in any string field

This upgrade ensures you never miss a detail when tracking how your AI resources evolve over time.

🐍 Code Interpreter: Native SDK Integration​

ToothFairyAI Python SDK Built-In​

The code interpreter now includes the ToothFairyAI Python SDK by default, enabling agents to natively perform programmatic actions within your workspace.

New Capabilities:

  • Native SDK Access - Agents can import and use the ToothFairyAI SDK without any additional setup
  • Workspace Operations - Perform programmatic actions directly within the workspace environment
  • Agent-to-Agent Communication - Programmatically call other agents inside the same workspace for complex orchestrations
  • Seamless Integration - No configuration required—SDK is available immediately in code interpreter sessions
  • Enhanced Automation - Build sophisticated workflows that leverage multiple agents programmatically

This integration transforms the code interpreter into a powerful control centre for building complex, multi-agent applications.

🎯 Massively Improved Plan Mode​

Multiple Choice Questions with Agent Recommendations​

Plan Mode has been massively enhanced to provide a more interactive and flexible planning experience, now supporting multiple choice questions with intelligent agent recommendations.

Key Enhancements:

  • Multiple Choice Interactions - Users can now respond to agent questions by selecting from recommended options
  • Smart Recommendations - Agents provide intelligent suggestions based on context and goals
  • Flexible Input - Users can either select from choices OR type manual answers for maximum flexibility
  • Enhanced Operator Agent Planning - Improved core planning and tooling capabilities specifically for Operator agents
  • Agentic Tooling Integration - Full support for local folder operations within the planning workflow

This upgrade makes Plan Mode more intuitive and powerful, enabling richer human-agent collaboration during task execution.

🎨 Expanded Creative Access for Starter Plans​

Images, Videos & 3D Models for Everyone​

We're preparing for something big at the end of this month! As part of these preparations, we now allow Starter plans to create images, videos, and 3D models—capabilities previously available only on higher tiers.

What's New:

  • Image Generation - Starter plans can now create AI-generated images for their projects
  • Video Creation - Access to video generation capabilities across all subscription levels
  • 3D Model Generation - Create 3D models regardless of your plan tier
  • Feature Uniformisation - We're committed to making features available across subscriptions, gating only where it makes sense
  • More Coming Soon - Stay tuned for additional exciting announcements this month!

This democratisation of creative AI tools ensures everyone can bring their visions to life, regardless of subscription level.

🏆 Orchestrator Benchmarking​

Performance Testing for Workflow Orchestration​

Orchestrator agents can now be benchmarked just like standard agents, enabling comprehensive performance testing of complex workflows.

Benchmarking Capabilities:

  • Workflow Performance Testing - Measure how well orchestrators accomplish specific workflows
  • Condition-Based Evaluation - Test orchestrator performance under various conditions and scenarios
  • Standard Benchmarking Interface - Same familiar benchmarking tools you use for regular agents
  • Parallel Task Assessment - Evaluate how orchestrators handle multiple concurrent operations
  • Reliability Metrics - Track success rates, execution times, and resource efficiency

This is particularly important when you need to ensure your orchestration workflows perform consistently across different operational conditions.

🎙️ Improved Voice Cloning Experience​

Enhanced Visual Feedback & Guidance​

We've improved the voice cloning experience with much better visual feedback and step-by-step guidance to help users achieve the best possible voice synthesis results.

Enhancements:

  • Visual Progress Indicators - Clear visual cues showing each step of the cloning process
  • Guided Instructions - Step-by-step guidance on how to record samples for optimal results
  • Quality Feedback - Real-time feedback on recording quality and suitability for cloning
  • Best Practice Tips - In-context recommendations for microphone placement, environment, and speaking style
  • Error Prevention - Proactive warnings about common issues that could affect voice quality

These improvements ensure users can create high-quality voice clones with confidence, even if they're new to voice synthesis technology.

📋 Summary​

This update includes:

  • GraphQL API Tools - Native support for queries and mutations with full context-aware features
  • Enhanced Diff UI - Pinpoint precision for reviewing changes in Agents, Hooks, and Tools
  • Code Interpreter SDK - Built-in ToothFairyAI Python SDK for programmatic workspace operations
  • Improved Plan Mode - Multiple choice questions with recommendations and enhanced Operator agent capabilities
  • Creative Tools Access - Images, videos, and 3D models now available for Starter plans
  • Orchestrator Benchmarking - Performance testing for orchestrator agents and workflows
  • Voice Cloning UX - Better visual feedback and guidance for optimal voice synthesis results

Thank you for using ToothFairy! We're constantly working to improve your experience. If you have any feedback or encounter any issues, please don't hesitate to reach out to our support team at support@toothfairyai.com.

Keep building magic with AI! 🧙‍♀️✨

v0.673.0