Changelog

V1.0.0 - April 2026

V1.0 is the biggest update since the plugin’s creation. We are officially out of beta.

New Features

AI Agents

• Run Claude Code, Codex, GitHub Copilot, and Gemini CLI agents directly inside the editor
• Each agent has full access to all plugin tools via MCP
• Per-agent model selection and thinking effort control
• Concurrent agent instances on separate conversations
• One-click install buttons for each CLI

Free AI Usage

• Two built-in free-tier slots with real AI models
• No API key required, works immediately after activation
• Slot 1: ~5M tokens/24h reset
• Slot 2: ~300K tokens/6h reset with model picker

Tool Expansion (975 actions across 56 categories)

• Animation: BlendSpaces, Montages, AnimBP state machines, AnimGraph chains, IK, virtual bones, motion warping (65 actions)
• Sequencer: Level sequences, camera rigs, all track types, MRQ rendering (56 actions)
• Level Actors: Spawn, transform, physics, World Partition, HLODs, data layers (53 actions)
• Materials: Full graph editing, instances, functions, layers (40 actions)
• UMG Widgets: Full layout creation, animations, slot editing (31 actions)
• PCG: Graph building, mesh spawners, transform randomizers, generation (32 actions)
• Behavior Trees, State Trees, GAS, Audio, MetaSounds, Data Structures, Physics/Destruction, Environment, Control Rig, IK Retargeting, Pose Search, Chooser Tables, Splines, Landscape, NavMesh, Vehicles, Mass Entity, Geometry Script, Foliage, Rendering, Level Snapshots, Common UI, Live Link, Media, and more

Asset Generation

• Texture generation: Imagen, DALL-E, Together AI, OpenRouter
• PBR material generation: Auto-derived Normal/Roughness/Metallic/AO from single base texture
• 3D model generation: Text-to-3D and Image-to-3D via Meshy, Tripo, Hunyuan
• Sound generation: SFX, music, voice via multiple providers
• Material from textures: Auto-detect texture types and create complete materials

Voice Integration

• Speech-to-text via Whisper
• Text-to-speech with 6 voices (Alloy, Echo, Fable, Onyx, Nova, Shimmer)
• Auto-play AI responses
• Auto-send transcription
• Configurable TTS voice in Settings

Learning Ecosystem

• Skill tree with courses, lessons, milestones, and challenges
• XP, leveling, titles (Newcomer through Mythic)
• Daily login streaks
• Global leaderboard
• Achievement auto-detection
• Video tutorials

Project Intelligence

• Project Scanner with AI Q&A
• Interactive dependency graphs
• Inheritance tree visualization
• Pie charts and flowcharts in conversations
• Performance profiling with trace analysis
• AI Memory: persistent cross-session context
• GDD Manager: feed design documents to the AI
• Plan Manager: multi-step task tracking

UI & UX

• 20 languages supported
• Multiple theme system with customization
• Chat browser zoom (CTRL+wheel)
• Token counter per conversation
• Tool execution bubbles with success/error indicators
• Markdown rendering in chat
• @ asset mention system with popup picker
• File and image attachments
• Concurrent conversations with persistent history
• Flowchart rendering (inline and code-fence)

MCP Server

• TCP server on port 9877 for external AI tool integration
• Claude Desktop extension included
• Write-lock gate prevents zombie tool calls from previous sessions

Infrastructure

• Cloud asset updates: AI prompt files update from Supabase without plugin rebuild
• Welcome screen with announcements (20 languages)
• Built-in bug report system with image attachments
• Dynamic provider/model configuration from cloud
• 9 API key slots with ALT+1-9 hotkey switching

Improvements

• Incremental Blueprint graph building (one function at a time for faster AI thinking)
• Batch operations on most create/add/set/delete tools via items=[]
• Parallel tool execution within a single AI response
• Pre-flight validation system for Blueprint graph builds
• Idempotent asset creation (no overwrite dialogs)

Bug Fixes

• Fixed Gemini API timestamp field rejection
• Fixed PCG volume not snapping to landscape position
• Fixed Niagara crash when adding renderers after emitter removal
• Fixed Mac CLI detection for agents launched from Finder
• Fixed UE 5.7 welcome screen white screen (CEF LoadString regression)
• Fixed UE 5.7 ConcertSyncClient crash via MovieRenderPipeline dependency chain
• Fixed local LLM compatibility (content format flattening for Lemonade/Ollama/LM Studio)
• Fixed empty Authorization header rejection on local servers
• Fixed input action overwrite dialog on existing assets

Breaking Changes

• Minimum engine version is now UE 5.5 (was 5.4)
• Browser extension connection method removed (replaced by native AI agents)
• Plugin renamed from “Ultimate Blueprint Generator” to “Ultimate Engine Copilot”