Release v0.14.1 (#131)

# GAIA v0.14.1 Release Notes

## Overview

This release enhances the **Code Agent** with checklist-based
orchestration for web development, upgrades to **Lemonade Server
v9.1.0**, and fixes chat history persistence.

## What's New

### 🛠️ Code Agent Enhancements

New orchestration framework for building web applications:

- Checklist-driven workflows that break complex tasks into structured
steps
- Automatic project type detection (Next.js, Python) with appropriate
tooling
- Conversation history summarization for faster debugging cycles
- Validation tools for build, lint, and type-checking

```bash
gaia code "Create a task management app with user authentication"
```

### 🍋 Lemonade Server v9.1.0

- Upgraded to Lemonade Server v9.1.0
- Health check verifies Lemonade installation with clear error messages
if missing
- Context size validation ensures sufficient tokens before agent
execution

### 💬 Chat Improvements

- **History persistence fix**: Conversation history now properly saves
with `/save` and restores with `/resume`
- **Better no-document behavior**: Chat agent uses general knowledge
instead of failing when no documents are indexed

## Improvements

- **Linting:** Cross-platform linting script (`util/lint.py`) for
Windows/macOS/Linux
- **CI/CD:** New chat agent test workflow

## What's Changed

- GAIA Code Enhancements by @itomek
- Implement cross-platform linting script by @kovtcharov
- Add health check for Lemonade server installation by @kovtcharov
- Add context size validation for Lemonade server by @kovtcharov
- Fix Chat History Persistence by @kovtcharov
- Enhance chat agent behavior when no documents indexed by @kovtcharov
- Faster Web Dev Agent Iterations by @eddierichter-amd
- Update Lemonade version to 9.1.0 by @kovtcharov

**Full Changelog:**
v0.14.0...v0.14.1

V0.14.0 (#127)

# GAIA v0.14.0 Release Notes

  ## Overview

This release introduces the **Knowledge Assistant** for document Q&A
with agentic RAG, transitions to a streamlined **cross-platform
developer workflow** using `uv`, and includes Lemonade Server v9.0.8
with auto-start capabilities.

  ## Installation

  ```bash
  # Install uv (ultra-fast Python package manager)
  # Windows: irm https://astral.sh/uv/install.ps1 | iex
  # macOS/Linux: curl -LsSf https://astral.sh/uv/install.sh | sh

  git clone https://github.com/amd/gaia.git
  cd gaia
  uv venv .venv --python 3.12
  source .venv/bin/activate  # Windows: .\.venv\Scripts\Activate.ps1
  uv pip install -e .
  gaia -v
  ```

**Why uv?** 10-100x faster installs, automatic Python management,
cross-platform support (Windows/macOS/Linux), and editable installs.

> **Note:** As GAIA is upgraded, the above flow is the recommended one.
A new installer is coming in a future.

  ## What's New

  ### 📚 Knowledge Assistant - Document Q&A (#740)

  Chat with your documents using agentic RAG:

  - Index PDFs, markdown, text, CSV, JSON, and 30+ code file types
  - Semantic search with hybrid keyword boosting
  - VLM image extraction from PDFs
  - Auto-discovery: agent searches, indexes, and answers automatically

  ```bash
  gaia chat --index manual.pdf
  gaia rag quick report.pdf "What are the key findings?"
  gaia talk --index document.pdf
  ```

  ### 🍎 Cross-Platform Support (#948, #996)

  - Native macOS and Linux support
  - Removed Conda dependency, migrated to Python venv
  - macOS testing in CI/CD

  ### 🍋 Lemonade Server v9.0.8 Auto-Start (#973)

  - GAIA automatically starts Lemonade Server if not running
  - Version compatibility checks
  - `--base-url` support for custom endpoints

  ### ⬇️ Model Pull with Streaming Progress (#999)

  ```bash
  gaia model pull Qwen2.5-3B-Instruct-GGUF
  ```

  Download models with real-time progress updates and resume support.

  ### 🛠️ Code Agent Improvements (#856, #873, #898, #899, #950)

  - Enhanced debugging capabilities
  - Structured tool role messages
  - Bug fixes and deprecated tool cleanup

  ### 🔗 Unified --base-url CLI Support (#1012)

  Use custom Lemonade Server URLs across all commands:

  ```bash
  gaia chat --base-url http://custom-server:8000
  ```

  ## Improvements

- **Evaluation:** Transcript validation (#912), extended timeouts
(#947), resume/retry for groundtruth (#949)
  - **Security:** Path traversal prevention with PathValidator (#946)
- **Infrastructure:** Constants refactoring (#1029), localhost reference
updates (#980)
- **Developer Experience:** API documentation (#987), Lemonade MSI
installer (#983), Node.js v20 VSCode prereq (#981)
  - **CI/CD:** Workflow updates (#1017, #881)

  ## What's Changed

- Add agentic RAG and document Q&A by @kovtcharov in
aigdat/gaia#740
- Fixing the order of arguments in _fix_code_with_llm by
@eddierichter-amd in aigdat/gaia#898
- Removing reference to read_python_file by @eddierichter-amd in
aigdat/gaia#899
- Replacing "Previous Output" text with tool role messages by
@eddierichter-amd in aigdat/gaia#873
- Improvements to Debugging Capability of Gaia Code Agent by
@eddierichter-amd in aigdat/gaia#856
- Add transcript format validation by @kovtcharov in
aigdat/gaia#912
- Increase Lemonade client timeouts by @kovtcharov in
aigdat/gaia#947
- Add resume capability and retry support by @kovtcharov in
aigdat/gaia#949
- Add venv setup and macOS platform support by @kovtcharov in
aigdat/gaia#948
- Implement PathValidator for Path Traversal Prevention by @kovtcharov
in aigdat/gaia#946
  - Code Agent gap by @itomek in aigdat/gaia#950
- Update localhost references by @kovtcharov in
aigdat/gaia#980
- Create three specialized Claude agents by @itomek in
aigdat/gaia#984
- Lemonade MSI Installer by @itomek in
aigdat/gaia#983
- Fix GitHub Actions security warnings by @itomek in
aigdat/gaia#881
- Add Node.js v20.19.x to VSCode extension prerequisites by @Copilot in
aigdat/gaia#981
  - GAIA API docs by @itomek in aigdat/gaia#987
- Remove Conda Dependencies - Migrate to Python venv by @kovtcharov in
aigdat/gaia#996
- Lemonade Server v9.0.8 Upgrade & Auto-Start by @kovtcharov in
aigdat/gaia#973
- Add model pull command with streaming progress by @kovtcharov in
aigdat/gaia#999
- Add --base-url support across all CLI commands by @kovtcharov in
aigdat/gaia#1012
- Refactor GitHub Actions workflows by @kovtcharov in
aigdat/gaia#1017
- Update documentation and versioning by @kovtcharov in
aigdat/gaia#1014
- Refactor constants for improved maintainability by @kovtcharov in
aigdat/gaia#1029

**Full Changelog:**
aigdat/gaia@v0.13.0...v0.14.0

v0.13.0 (#113)

# GAIA v0.13.0 Release Notes

## Overview

This major release introduces **GAIA Code**, a proof-of-concept AI
coding agent with VSCode integration, and a **Docker Agent** for
containerized workflows. Most significantly, this release establishes a
new architecture that allows GAIA agents to be easily built, and to be
exposed via **API, MCP, and CLI**, opening up extensive possibilities
for agent composition and integration. The release also includes
improvements to the evaluation framework and enhanced documentation for
building custom agents.

## What's New

### 🚀 GAIA Code Agent with VSCode Integration (#774, #864)

Introduced a proof-of-concept AI-powered coding agent with Visual Studio
Code integration:

- **In-Editor Development**: Trigger GAIA Code Agent from VSCode via
extension coupled with GitHub Copilot
- **Automated Code Generation**: Generate Python code from natural
language descriptions
- **Test-Driven Development**: Automatic test generation and execution
- **Iterative Refinement**: Multi-iteration approach to code quality
- **File Context Awareness**: Automatic workspace file monitoring and
context

*Note: GAIA Code is currently a proof-of-concept focused on Python
development workflows.*

**Files Changed**: `src/gaia/agents/code/`, VSCode extension files

### 🐳 Docker Agent (#811, #833)

New proof-of-concept Docker agent for containerized application
development:

- **Container Management**: Create, start, stop, and manage Docker
containers
- **Image Building**: Automated Dockerfile generation and image builds
- **Docker Compose Support**: Multi-container orchestration capabilities
- **Isolated Environments**: Containerized development environments for
projects

*Note: The Docker Agent is currently a proof-of-concept demonstrating
containerized workflow automation.*

### 🏗️ Agent Architecture: Multi-Protocol Exposure (#846)

**Major architectural enhancement** enabling GAIA agents to be exposed
through multiple interfaces:

- **API Exposure**: RESTful API endpoints for agent interactions
- **MCP (Model Context Protocol)**: Native MCP server support for agent
communication
- **CLI Interface**: Command-line access to agent capabilities
- **Unified Pattern**: Class inheritance-based design pattern for
building new agents

This architecture opens up powerful possibilities:
- Integrate agents into existing tools and workflows
- Build custom agents using established patterns
- Mix and match communication protocols based on needs

## Improvements

### 🔧 Evaluation Framework Improvements

#### Fix: Remove Silent Fallback in Transcript Matching (#843)

Improved error handling in evaluation transcript matching:

- **Fail-Fast Approach**: Clear failures instead of silent fallbacks
- **Better Debugging**: Improved error messages for mismatches
- **Data Integrity**: Ensures evaluation data consistency

#### Restore Python Execution Tools (#839)

Re-added essential Python execution capabilities:

- Restored `run_test` tool for test execution
- Restored `execute_python_file` tool for script running
- Better integration with code agent workflows

## Getting Started with Custom Agents

With the new agent architecture, building custom agents is
straightforward. Agents can inherit from base classes and automatically
gain API, MCP, and CLI exposure. See the updated documentation for
examples and best practices.

V0.12.1 (#106)

# GAIA v0.12.1 Release Notes

## Overview

This patch release focuses on bug fixes and improvements to the
evaluation framework, particularly addressing issues with the
visualization and reporting tools. All changes improve the reliability
and usability of the `gaia eval`, `gaia visualize`, and `gaia report`
commands.

## What's Changed

### Bug Fixes

#### 🔧 Fix Evaluation Visualizer Model Count and Path Issues (#823)

Fixed multiple critical issues in the `gaia visualize` and `gaia report`
commands:

- **Incorrect Model Count in Consolidated Report**: Fixed model count
calculation in the webapp to show the correct number of models (was
showing only 4 instead of 8)
- Now calculates unique models directly from `metadata.evaluation_files`
instead of filtered/grouped data

- **Windows Path Separator Bug**: Fixed cross-platform compatibility
issue in `isMainEvaluationEntry()` function
- Now handles both Unix (`/`) and Windows (`\`) path separators
correctly

- **Incorrect Default Directory Paths**: Updated default paths to match
actual evaluation output locations
- Changed from `workspace/evaluation` to `workspace/output/evaluations`
- Changed from `workspace/experiments` to `workspace/output/experiments`

- **Outdated Report Filename**: Updated default report filename from
`LLM_RAG_Evaluation_Report.md` to `LLM_Evaluation_Report.md`
- Better reflects support for multiple evaluation types (RAG,
summarization, etc.)

**Files Changed**: `src/gaia/cli.py`, `src/gaia/eval/eval.py`,
`src/gaia/eval/webapp/public/app.js`

### Improvements

#### 📊 Standardize Evaluation Workflow Default Directories (#820)

Implemented consistent default parameters across all evaluation commands
with a unified directory structure:

```
./output/
├── test_data/          # gaia generate
├── groundtruth/        # gaia groundtruth
├── experiments/        # gaia batch-experiment
└── evaluations/        # gaia eval
```

**Key Changes**:
- Added centralized directory constants in `cli.py`
- Added `GAIA_WORKSPACE` environment variable support for flexible
workspace management
- Updated all command defaults to use the new structure
- Updated documentation in `docs/eval.md` and `docs/cli.md`

**Benefits**:
- Consistency: All evaluation artifacts organized in one location
- Maintainability: Centralized constants eliminate duplication
- Flexibility: Workspace environment variable for managing multiple
projects
- Cleanup: Single directory to clean or ignore

**Files Changed**: Multiple files including CLI, evaluation modules,
webapp components, and documentation

#### 🏷️ Improve Reporting for Cloud Model Identifiers (#834)

Enhanced model counting logic in the Evaluation Visualizer to support
additional cloud model identifiers:

- Added support for 'gpt-4' and 'gemini' model identifiers
- Improved accuracy of model classification in reports

**Files Changed**: `src/gaia/eval/webapp/public/app.js`

## Contributors

- Kalin Ovtcharov (@kalin-ovtcharov)

## Upgrade Notes

If you have existing evaluation workflows, note the following directory
changes:

- `./evaluation` → `./output/evaluations`
- `./experiments` → `./output/experiments`

You can set the `GAIA_WORKSPACE` environment variable to use a custom
workspace location if needed.

---

**Full Changelog**:
v0.12.0...v0.12.1

Release v0.12.0 - Docker Agent Integration (#105)

# Release v0.12.0 - Docker Agent Integration

## Features & Enhancements

### Docker Agent Integration (#810, #811)
- Added Docker agent for natural language containerization with
AI-powered Dockerfile generation
- Implemented modular MCP architecture with per-agent server support
using FastMCP
- Created `gaia mcp docker` command for standalone Docker agent MCP
server
- Added Docker application framework for testing and demonstrations
- Enhanced agent system with MCPAgent base class for Model Context
Protocol support

### Model Improvements
- Updated default model to Qwen3-Coder-30B-A3B-Instruct-GGUF for
improved code generation performance
- Optimized Dockerfile generation with multi-step planning and
validation

### Architecture Improvements
- Implemented AgentMCPServer for wrapping MCP agents and exposing them
via HTTP + JSON-RPC
- Refactored MCP transport layer for better modularity and agent
isolation
- Enhanced agent execution with detailed status reporting and result
handling

### Documentation
- Comprehensive Docker agent documentation with setup and usage examples
(docker.md)
- Updated MCP documentation with Docker agent integration guide (mcp.md)
- Added CLI examples for Docker agent workflows

v0.11.2 (#104)

# Release Notes - v0.11.2

## Features & Enhancements

### Eval Framework Improvements (#784)
- Added chat template support for better model compatibility
- Implemented thinking token extraction for advanced analysis
- Enhanced batch experiment runner with multi-model configuration
support
- Expanded evaluation documentation and webapp UI improvements
- Added new `multi_model_summarization.json` configuration

## Updates

### Lemonade Backend (#818)
- Updated to Lemonade v8.1.12

## Documentation

### Developer Documentation (#803)
- Clarified repository structure and development workflow
- Updated release process documentation

## Changes Summary
- 20 files changed, 948 insertions(+), 603 deletions(-)
- Focus areas: evaluation framework enhancements, model compatibility,
and documentation clarity

Release v0.11.1 (#101)

## Architecture Improvements

- Code quality improvements — Improved static analysis and cleaned up
the codebase
- Static analysis cleanup — Resolved warnings and reduced false
positives

## Testing & CI/CD

- Lint workflow — Expanded CI to run comprehensive linting, type checks,
security scans, and import smoke tests
- Local dev tooling — Added a helper script (util/lint.ps1) to run and
optionally fix checks locally

## Bug Fixes

- Filesystem — Prevent unintended directory creation when no new
directory is required

## Documentation

- Model installation — Clarified how to install/manage additional models
via Lemonade model manager; cross-linked in CLI guide and FAQ

**Full Changelog**: v0.11.0...v0.11.1

Release v0.11.0 (#96)

### App Development Framework

Electron-based framework for building AI-powered desktop applications.

- Example app template — Ready-to-use MCP integration demo
- NPM integration — Streamlined development workflows
- CI/CD automation — GitHub workflows for building and packaging

### JAX Desktop Application

Electron-based Jira Dashboard with integrated AI assistant.

- Desktop App — Projects, issues, search, and creation
- System status — Real-time GAIA and MCP Bridge monitoring
- AI chat assistant — Context-aware help for Jira workflows

### n8n Workflow Integration

Complete integration guide with pre-built workflow templates.

- Pre-built templates — Common automation scenarios
- HTTP integration — Simple REST API calls to MCP server
- Example workflows — Email summarization, Jira automation, content
generation

## Architecture Improvements

- Enhanced agent system — Improved state management and tool registry
- Blender agent refactoring — Package renamed to lowercase
agents/blender/ for consistency
- Streaming support — Real-time response streaming throughout agent
interactions

## Testing & CI/CD

- Jira agent tests — Complete test suite with interactive mode
- MCP integration tests — Dedicated test workflows for Windows and Linux
- Enhanced CI/CD — App building workflows and automated testing

## Documentation

New comprehensive guides for MCP integration, n8n workflows, Jira agent
usage, and app development.




https://github.com/user-attachments/assets/ebbab2af-7051-4ae8-9064-2a651489d54d

v0.10.1 (#90)

## GAIA v0.10.1 Release Notes

### 🌟 TL;DR - Key Highlights

- 📄 **Document Q&A Evaluation** - Process PDF documents and evaluate AI
models on question-answering tasks
- 🛠️ **Installation Fixes** - Resolved critical installer issues with
shortcuts and CLI launching
- 🔧 **Build Infrastructure** - Added GitHub workflows for future app
distribution
- 🔄 **Updated Dependencies** - Latest RAUX (v0.2.4) and Lemonade
(v8.1.5) for improved stability

### 🚀 New Features

#### Document Q&A Evaluation Support
Enhanced the evaluation framework with comprehensive PDF processing
capabilities for question-answering experiments.

- **PDF text extraction** using the `pypdf` library for local document
processing
- **Dedicated Q&A configuration** (`basic_qa.json`) for document-based
evaluation experiments
- **Enhanced groundtruth consolidation** for Q&A pairs and RAG use cases
- **Document content caching** for improved performance during batch
experiments

**💡 Quick Start:**
```bash
# Generate Q&A groundtruth from PDFs
gaia groundtruth -d ./data/pdf --use-case qa --num-samples 3 -o ./groundtruth

# Run Q&A experiments
gaia batch-experiment -c ./src/gaia/eval/configs/basic_qa.json -i ./groundtruth/consolidated_qa_groundtruth.json -o ./experiments

# Evaluate and visualize results
gaia eval -d ./experiments -o ./evaluation
gaia visualize --experiments-dir ./experiments --evaluations-dir ./evaluation
```

## GitHub Workflows for App Distribution

### Added foundational infrastructure for building and packaging GAIA
mini-apps:
- PR validation workflows for app builds
- Release build automation
- Automated packaging workflows

## 🐛 Bug Fixes
- Fix gaia `visualize` webapp `not found` error
- Installer improvements - Fixed NSIS installer flow for proper shortcut
creation after RAUX installation
- CLI launching - Resolved issues with launch_gaia.bat --cli execution
- Package distribution - Added missing package extras
([talk,dev,eval,youtube,audio]) to installer
- CI/CD enhancements - Improved release script to exclude test workflows
from distribution

## 🔄 Updates
- RAUX Integration updated to version 0.2.4 (v0.6.5+raux.0.2.4) fixing
installation failures that showed blank screens instead of error
messages in the terminal display
- Lemonade Backend updated to version 8.1.5 for improved performance and
stability
- Package structure - Updated setup.py with complete module structure
(chat, talk, apps, eval, mcp, agents)
- Added Discord label

## 📖 Documentation
The Document Q&A evaluation workflow is documented in detail at

https://github.com/aigdat/gaia/blob/main/docs/eval.md#workflow-3-document-qa.

v0.10.0 (#80)

## 🌟 TL;DR - Key Highlights

- 🧪 **Complete Evaluation Framework** - Generate synthetic test data,
run batch experiments, and visualize results with interactive web
dashboard
- 🐧 **Linux Support** - Native CLI and UI (RAUX) support for Ubuntu with
unified cross-platform installation (currently supports iGPU via
llama.cpp/Vulkan backend using the Lemonade server)
- 🗣️ **Enhanced Voice & Chat and new SDKs** - Introduced a new Talk SDK
with real-time transcription and comprehensive Chat SDK with
conversation memory
- 📝 **AI Summarizer** - Intelligent meeting transcript and email
summarization with multiple output formats (PDF, HTML, JSON)
- 🎨 **Blender Integration** - Natural language 3D modeling through MCP
server with real-time scene manipulation

## ⚠️ Breaking Changes

- **CLI Command Update**: `gaia-cli` has been renamed to `gaia`
throughout the codebase
  - **Before**: `gaia-cli llm "Hello world"`
  - **After**: `gaia llm "Hello world"`
- **Agent Server Architecture**: Removed HTTP/WebSocket agent server
dependencies for text-based interactions
- **Parameter Changes**: Removed `--agent-name`, `--host`, `--port`
parameters from `prompt`, `chat`, `talk`, and `stats` commands

## 🚀 Major Features

### Enhanced Evaluation Framework
- **Comprehensive workflow documentation** with step-by-step examples
for meeting transcripts, emails, document Q&A, and third-party model
testing
- **Improved evaluation metrics** with time tracking for summary
generation and percentage-based quality scores
- **Robust experiment management** with crash recovery and selective
re-runs for new models
- **Enhanced reporting** with final results tables, bar charts, and
colored score legends
- **Interactive web visualization tool** for exploring evaluation
results with real-time experiment comparison
- **Synthetic data generation** for creating test datasets without
privacy concerns

**📖 Documentation:** See
[eval.md](https://github.com/amd/gaia/blob/main/docs/eval.md) for
complete evaluation workflows

**💡 Quick Start:**
```bash
# Complete evaluation workflow
gaia groundtruth -d ./test_data --use-case summarization -o ./groundtruth
gaia batch-experiment -c experiment_config.json -i ./groundtruth/consolidated_summarization_groundtruth.json -o ./experiments
gaia visualize --experiments-dir ./experiments --evaluations-dir ./evaluation
```

### Linux Platform Support
- **Full Linux CLI support** with complete Lemonade server integration
- **Cross-platform Python isolation** using standalone distributions
- **Enhanced CI/CD pipeline** with dedicated Linux testing workflows
- **GAIA UI (RAUX) Linux support** with native Ubuntu compatibility and
unified installation strategy

**📖 Documentation:** See
[cli.md](https://github.com/amd/gaia/blob/main/docs/cli.md) for
cross-platform usage and
[ui.md](https://github.com/amd/gaia/blob/main/docs/ui.md) for UI setup
**💡 Try it:** `gaia --version` or `gaia llm "Hello from Linux!"`

### Talk SDK and Audio Pipeline
- **Unified voice/text chat integration** with comprehensive SDK
- **Improved audio processing** with real-time transcription and
diagnostics
- **LLMClient streaming integration** replacing WebSocket architecture

**📖 Documentation:** See
[talk.md](https://github.com/amd/gaia/blob/main/docs/talk.md) for voice
interaction setup
**💡 Try it:** `gaia talk --help` or start a voice conversation with
`gaia talk`

### GAIA Summarizer Tool
- **AI-powered summarization** for meeting transcripts and emails
- **Multiple output formats** (JSON, PDF, HTML, email) with batch
processing
- **Customizable summary styles** (executive, bullets, detailed, action
items)
- **Auto-detection** of content type (transcript vs email) for optimized
processing
- **Batch processing** for entire directories of files

**📖 Documentation:** See
[cli.md](https://github.com/amd/gaia/blob/main/docs/cli.md) and
[features.md](https://github.com/amd/gaia/blob/main/docs/features.md)
for complete summarization workflows and all available options

**💡 Quick Start:**
```bash
# Summarize meeting transcript with multiple styles
gaia summarize -i meeting_transcript.txt --styles executive action_items
```

### Chat SDK
- **Comprehensive chat interface** with conversation memory and session
management
- **Multiple abstraction levels** from simple one-off questions to
advanced session handling
- **Assistant naming support** for personalized AI interactions
- **Streaming responses** with real-time output in interactive mode
- **Rich interactive commands** (`/clear`, `/history`, `/system`,
`/model`, `/stats`)

**📖 Documentation:** See `chat.md` for SDK integration guide

**💡 Quick Start:**
```bash
# Interactive chat with conversation memory
gaia chat
```

### Enhanced Blender Integration
- **Natural language 3D modeling** through MCP (Model Context Protocol)
server integration
- **Comprehensive scene management** with object creation, materials,
and transformations
- **Interactive planning system** for complex 3D scene creation
- **CLI command support** with example-based learning and custom queries
- **Real-time Blender communication** for immediate 3D visualization

**📖 Documentation:** See
[blender.md](https://github.com/amd/gaia/blob/main/docs/blender.md) for
setup and MCP server configuration

**💡 Quick Start:**
```bash
# Natural language 3D modeling
gaia blender --query "Create a red cube and blue sphere"
```

## 🔧 Architecture Improvements

- **Simplified CLI architecture** with direct LLM communication (removed
agent server dependencies)
- **Enhanced Blender MCP integration** with real-time 3D scene
manipulation
- **Improved error handling** and resource cleanup across components
- **Performance optimizations** for cross-platform deployment

## 🐛 Bug Fixes

- **Chat CLI improvements** with restored interactive conversation
support and conversation history management
- **Talk CLI enhancements** with improved audio processing and real-time
transcription reliability
- **Installation verification fixes** with simplified Lemonade
verification and enhanced logging
- **Cross-platform compatibility** improvements for both Windows and
Linux environments

## 📖 Documentation & Tooling

- **Comprehensive evaluation documentation** with practical examples and
workflows
- **Cost estimation tools** for Claude API usage tracking with detailed
breakdowns
- **Enhanced testing infrastructure** with dedicated Chat SDK CI
workflows
- **Updated installation processes** with improved reliability
- **Interactive web applications** for evaluation visualization and
result exploration

## 🚀 Installation & Upgrade

### Quick Installation
- **Windows**: Simply download and run
[gaia-windows-setup.exe](https://github.com/amd/gaia/releases/download/v0.10.0/gaia-windows-setup.exe)
- **Linux (UI)**: Follow the steps outlined in the [UI installation
guide](https://github.com/amd/gaia/blob/main/docs/ui.md)
- **Linux (CLI)**: Follow the steps outlined in the [GAIA developer
guide](https://github.com/amd/gaia/blob/v0.10.0/docs/dev.md#setup-and-installation)

### Developer Installation
```bash
# Install GAIA with all features
pip install -e .[talk,dev,eval]

### Upgrading from v0.9.x
```bash
# Update your installation
pip install --upgrade gaia

# Update CLI commands (breaking change)
# Old: gaia-cli llm "Hello"
# New: gaia llm "Hello"

# Verify installation
gaia --version
gaia llm "Test query to verify functionality"
```

### Requirements
- **Lemonade Server**: Required for LLM functionality (`lemonade-server serve`)
- **Blender 4.3+**: Required for 3D modeling features
- **Node.js**: Required for evaluation web visualizer