dexto 1.1.2 → 1.1.4

package/dist/agents/agent-registry.json

@@ -0,0 +1,67 @@
+{
+  "version": "1.0.0",
+  "agents": {
+    "database-agent": {
+      "description": "AI agent for database operations and SQL queries",
+      "author": "Truffle AI",
+      "tags": ["database", "sql", "data", "queries"],
+      "source": "database-agent/",
+      "main": "database-agent.yml"
+    },
+    "talk2pdf-agent": {
+      "description": "PDF document analysis and conversation",
+      "author": "Truffle AI",
+      "tags": ["pdf", "documents", "analysis", "conversation"],
+      "source": "talk2pdf-agent/",
+      "main": "talk2pdf-agent.yml"
+    },
+    "image-editor-agent": {
+      "description": "AI agent for image editing and manipulation",
+      "author": "Truffle AI",
+      "tags": ["images", "editing", "graphics", "visual"],
+      "source": "image-editor-agent/",
+      "main": "image-editor-agent.yml"
+    },
+    "music-agent": {
+      "description": "AI agent for music creation and audio processing",
+      "author": "Truffle AI",
+      "tags": ["music", "audio", "creation", "sound"],
+      "source": "music-agent/",
+      "main": "music-agent.yml"
+    },
+    "product-researcher": {
+      "description": "AI agent for product name research and branding",
+      "author": "Truffle AI",
+      "tags": ["product", "research", "branding", "naming"],
+      "source": "product-name-researcher/",
+      "main": "product-name-researcher.yml"
+    },
+    "triage-agent": {
+      "description": "Customer support triage system",
+      "author": "Truffle AI",
+      "tags": ["support", "triage", "routing", "multi-agent"],
+      "source": "triage-demo/",
+      "main": "triage-agent.yml"
+    },
+    "nano-banana-agent": {
+      "description": "AI agent for advanced image generation and editing using Google's Nano Banana (Gemini 2.5 Flash Image)",
+      "author": "Truffle AI",
+      "tags": ["images", "generation", "editing", "ai", "nano-banana", "gemini"],
+      "source": "nano-banana-agent/",
+      "main": "nano-banana-agent.yml"
+    },
+    "podcast-agent": {
+      "description": "Advanced podcast generation agent using Google Gemini TTS for multi-speaker audio content",
+      "author": "Truffle AI",
+      "tags": ["podcast", "audio", "tts", "speech", "multi-speaker", "gemini"],
+      "source": "podcast-agent/",
+      "main": "podcast-agent.yml"
+    },
+    "default-agent": {
+      "description": "Default Dexto agent with filesystem and playwright tools",
+      "author": "Truffle AI", 
+      "tags": ["default", "filesystem", "playwright"],
+      "source": "default-agent.yml"
+    }
+  }
+}

package/dist/agents/agent-template.yml

@@ -0,0 +1,67 @@
+# Template for dexto create-app
+# describes the mcp servers to use
+mcpServers:
+  filesystem:
+    type: stdio
+    command: npx
+    args:
+      - -y
+      - "@modelcontextprotocol/server-filesystem"
+      - .
+  playwright:
+    type: stdio
+    command: npx
+    args:
+      - -y
+      - "@playwright/mcp@latest"
+
+# System prompt configuration - defines the agent's behavior and instructions
+systemPrompt:
+  contributors:
+    - id: primary
+      type: static
+      priority: 0
+      content: |
+        You are a helpful AI assistant with access to tools.
+        Use these tools when appropriate to answer user queries.
+        You can use multiple tools in sequence to solve complex problems.
+        After each tool result, determine if you need more information or can provide a final answer.
+    - id: dateTime
+      type: dynamic
+      priority: 10
+      source: dateTime
+      enabled: true
+
+# LLM configuration - describes the language model to use
+llm:
+  provider: openai
+  model: gpt-4.1-mini
+  apiKey: $OPENAI_API_KEY
+  
+# Alternative LLM providers (replace the above llm section with one of these):
+# Google Gemini:
+# llm:
+#   provider: google
+#   model: gemini-2.5-pro
+#   apiKey: $GOOGLE_GENERATIVE_AI_API_KEY
+#
+# Anthropic Claude:
+# llm:
+#   provider: anthropic
+#   model: claude-4-sonnet-20250514
+#   apiKey: $ANTHROPIC_API_KEY
+#
+
+# Storage configuration - uses a two-tier architecture: cache (fast, ephemeral) and database (persistent, reliable)
+# Memory cache with file-based database (good for development with persistence)
+storage:
+  cache:
+    type: in-memory
+  database:
+    type: sqlite
+
+# Tool confirmation configuration - auto-approve for better development experience
+toolConfirmation:
+  mode: auto-approve
+  timeout: 120000
+  allowedToolsStorage: memory

package/dist/agents/default-agent.yml

@@ -0,0 +1,64 @@
+# describes the mcp servers to use
+mcpServers:
+  filesystem:
+    type: stdio
+    command: npx
+    args:
+      - -y
+      - "@modelcontextprotocol/server-filesystem"
+      - .
+  playwright:
+    type: stdio
+    command: npx
+    args:
+      - -y
+      - "@playwright/mcp@latest"
+
+  # hf:
+  #   type: stdio
+  #   command: npx
+  #   args:
+  #     - -y
+  #     - "@llmindset/mcp-hfspace"
+
+# System prompt configuration - defines the agent's behavior and instructions
+systemPrompt:
+  contributors:
+    - id: primary
+      type: static
+      priority: 0
+      content: |
+        You are a helpful AI assistant with access to tools.
+        Use these tools when appropriate to answer user queries.
+        You can use multiple tools in sequence to solve complex problems.
+        After each tool result, determine if you need more information or can provide a final answer.
+    - id: dateTime
+      type: dynamic
+      priority: 10
+      source: dateTime
+      enabled: true
+
+# Optional greeting shown at chat start (UI can consume this)
+greeting: "Hi! I’m Dexto — how can I help today?"
+
+# # describes the llm configuration
+llm:
+  provider: openai
+  model: gpt-5-mini
+  apiKey: $OPENAI_API_KEY
+
+# Storage configuration - uses a two-tier architecture: cache (fast, ephemeral) and database (persistent, reliable)
+# Memory cache with file-based database (good for development with persistence)
+storage:
+  cache:
+    type: in-memory
+  database:
+    type: sqlite
+    # path: ./data/dexto.db
+
+## To use Google Gemini, replace the LLM section with Google Gemini configuration below
+## Similar for anthropic/groq/etc.
+# llm:
+#   provider: google
+#   model: gemini-2.0-flash
+#   apiKey: $GOOGLE_GENERATIVE_AI_API_KEY

package/dist/agents/nano-banana-agent/README.md

@@ -0,0 +1,200 @@
+# Nano Banana Agent
+
+A Dexto agent that provides access to Google's **Gemini 2.5 Flash Image** model for image generation and editing through a lean, powerful MCP server.
+
+## 🎯 What is Gemini 2.5 Flash Image?
+
+Gemini 2.5 Flash Image is Google's cutting-edge AI model that enables:
+- **Near-instantaneous** image generation and editing
+- **Object removal** with perfect background preservation
+- **Background alteration** while maintaining subject integrity
+- **Image fusion** for creative compositions
+- **Style modification** with character consistency
+- **Visible and invisible watermarks** (SynthID) for digital safety
+
+## 🚀 Key Features
+
+### Core Capabilities
+- **Image Generation**: Create images from text prompts with various styles and aspect ratios
+- **Image Editing**: Modify existing images based on natural language descriptions
+- **Object Removal**: Remove unwanted objects while preserving the background
+- **Background Changes**: Replace backgrounds while keeping subjects intact
+- **Image Fusion**: Combine multiple images into creative compositions
+- **Style Transfer**: Apply artistic styles to images
+
+### Advanced Features
+- **Character Consistency**: Maintain facial features and identities across edits
+- **Scene Preservation**: Seamless blending with original lighting and composition
+- **Multi-Image Processing**: Handle batch operations and complex compositions
+- **Safety Features**: Built-in safety filters and provenance signals
+
+## 🛠️ Setup
+
+### Prerequisites
+- Dexto framework installed
+- Google AI API key (Gemini API access)
+- Node.js 20.0.0 or higher
+
+### Installation
+1. **Set up environment variables**:
+   ```bash
+   export GOOGLE_GENERATIVE_AI_API_KEY="your-google-ai-api-key"
+   # or
+   export GEMINI_API_KEY="your-google-ai-api-key"
+   ```
+
+2. **Run the agent** (the MCP server will be automatically downloaded via npx):
+   ```bash
+   # From the dexto repository root
+   npx dexto -a agents/nano-banana-agent/nano-banana-agent.yml
+   ```
+
+The agent configuration uses `npx @truffle-ai/nano-banana-server` to automatically download and run the latest version of the MCP server.
+
+## 📋 Available Tools
+
+The agent provides access to 3 essential tools:
+
+### 1. `generate_image`
+Generate new images from text prompts.
+
+**Example:**
+```
+Generate a majestic mountain landscape at sunset in realistic style with 16:9 aspect ratio
+```
+
+### 2. `process_image`
+Process existing images based on detailed instructions. This tool can handle any image editing task including object removal, background changes, style transfer, adding elements, and more.
+
+**Example:**
+```
+Remove the red car in the background from /path/to/photo.jpg
+```
+
+**Example:**
+```
+Change the background of /path/to/portrait.jpg to a beach sunset with palm trees
+```
+
+**Example:**
+```
+Apply Van Gogh painting style with thick brushstrokes to /path/to/photo.jpg
+```
+
+### 3. `process_multiple_images`
+Process multiple images together based on detailed instructions. This tool can combine images, create collages, blend compositions, or perform any multi-image operation.
+
+**Example:**
+```
+Place the person from /path/to/person.jpg into the landscape from /path/to/landscape.jpg as if they were standing there
+```
+
+## 📤 Response Format
+
+Successful operations return both image data and metadata:
+```json
+{
+  "content": [
+    {
+      "type": "image",
+      "data": "base64-encoded-image-data",
+      "mimeType": "image/png"
+    },
+    {
+      "type": "text",
+      "text": "{\n  \"output_path\": \"/absolute/path/to/saved/image.png\",\n  \"size_bytes\": 12345,\n  \"format\": \"image/png\"\n}"
+    }
+  ]
+}
+```
+
+## 🎨 Popular Use Cases
+
+### 1. **Selfie Enhancement**
+- Remove blemishes and unwanted objects
+- Change backgrounds for professional photos
+- Apply artistic filters and styles
+- Create figurine effects (Nano Banana's signature feature)
+
+### 2. **Product Photography**
+- Remove backgrounds for clean product shots
+- Add or remove objects from scenes
+- Apply consistent styling across product images
+
+### 3. **Creative Compositions**
+- Fuse multiple images into unique scenes
+- Apply artistic styles to photos
+- Create imaginative scenarios from real photos
+
+### 4. **Content Creation**
+- Generate images for social media
+- Create variations of existing content
+- Apply brand-consistent styling
+
+## 🔧 Configuration
+
+### Environment Variables
+- `GOOGLE_GENERATIVE_AI_API_KEY` or `GEMINI_API_KEY`: Your Google AI API key (required)
+
+### Agent Settings
+- **LLM Provider**: Google Gemini 2.5 Flash
+- **Storage**: In-memory cache with SQLite database
+- **Tool Confirmation**: Auto-approve mode for better development experience
+
+## 📁 Supported Formats
+
+**Input/Output Formats:**
+- JPEG (.jpg, .jpeg)
+- PNG (.png)
+- WebP (.webp)
+- GIF (.gif)
+
+**File Size Limits:**
+- Maximum: 20MB per image
+- Recommended: Under 10MB for optimal performance
+
+## 🎯 Example Interactions
+
+### Generate a Creative Image
+```
+User: "Generate a futuristic cityscape at night with flying cars and neon lights"
+Agent: I'll create a futuristic cityscape image for you using Nano Banana's image generation capabilities.
+```
+
+### Remove Unwanted Objects
+```
+User: "Remove the power lines from this photo: /path/to/landscape.jpg"
+Agent: I'll remove the power lines from your landscape photo while preserving the natural background.
+```
+
+### Create Figurine Effect
+```
+User: "Transform this selfie into a mini figurine on a desk: /path/to/selfie.jpg"
+Agent: I'll create Nano Banana's signature figurine effect, transforming your selfie into a mini figurine displayed on a desk.
+```
+
+### Change Background
+```
+User: "Change the background of this portrait to a professional office setting: /path/to/portrait.jpg"
+Agent: I'll replace the background with a professional office setting while keeping you as the main subject.
+```
+
+## 🔒 Safety & Ethics
+
+Nano Banana includes built-in safety features:
+- **SynthID Watermarks**: Invisible provenance signals
+- **Safety Filters**: Content moderation and filtering
+- **Character Consistency**: Maintains identity integrity
+- **Responsible AI**: Designed to prevent misuse
+
+## 🤝 Contributing
+
+We welcome contributions! Please see our [Contributing Guidelines](../../CONTRIBUTING.md) for details.
+
+## 📄 License
+
+This project is licensed under the MIT License - see the [LICENSE](../../LICENSE) file for details.
+
+---
+
+**Note**: This agent provides access to Google's Gemini 2.5 Flash Image model through the MCP protocol. The implementation returns both image content (base64-encoded) and text metadata according to MCP specifications, allowing for direct image display in compatible clients. A valid Google AI API key is required and usage is subject to Google's terms of service and usage limits.

package/dist/agents/nano-banana-agent/nano-banana-agent.yml

@@ -0,0 +1,68 @@
+# Dexto Agent Configuration for Nano Banana (Gemini 2.5 Flash Image) MCP Server
+# Generated on 2025-01-27T00:00:00.000Z
+
+systemPrompt: |
+  You are an AI assistant specialized in advanced image generation and editing using Google's Nano Banana (Gemini 2.5 Flash Image) model. You have access to cutting-edge AI tools for:
+
+  - **Image Generation**: Create stunning images from text prompts with various styles and aspect ratios
+  - **Image Editing**: Modify existing images using natural language descriptions
+  - **Object Removal**: Remove unwanted objects while perfectly preserving the background
+  - **Background Changes**: Replace backgrounds seamlessly while keeping subjects intact
+  - **Image Fusion**: Combine multiple images into creative compositions
+  - **Style Transfer**: Apply artistic styles to images with character consistency
+  - **Advanced Features**: Character consistency, scene preservation, and multi-image processing
+
+  When working with images:
+  1. Always validate that input images exist and are in supported formats (JPG, PNG, WebP, GIF)
+  2. Provide clear feedback about what operations you're performing
+  3. Save processed images with descriptive names
+  4. Include image information (dimensions, file size, format) in your responses
+  5. Suggest additional enhancements and creative possibilities when appropriate
+  6. Leverage Nano Banana's signature features like the figurine effect and character consistency
+
+  Key Nano Banana Capabilities:
+  - **Near-instantaneous** processing with high visual coherence
+  - **Character consistency** across multiple edits
+  - **Scene preservation** with seamless background blending
+  - **Safety features** including SynthID watermarks
+  - **Multi-image processing** for complex compositions
+
+  Popular use cases:
+  - Selfie enhancement and creative variations
+  - Product photography with clean backgrounds
+  - Artistic style applications
+  - Object removal from photos
+  - Background replacement for portraits
+  - Creating figurine effects (Nano Banana's signature feature)
+  - Image fusion for creative compositions
+
+  Supported image formats: JPG, JPEG, PNG, WebP, GIF
+  Maximum file size: 20MB per image
+
+mcpServers:
+  nano_banana:
+    type: stdio
+    command: npx
+    args:
+      - -y
+      - "@truffle-ai/nano-banana-server"
+    connectionMode: strict
+    env:
+      GEMINI_API_KEY: $GOOGLE_GENERATIVE_AI_API_KEY
+    timeout: 60000
+
+toolConfirmation:
+  mode: "auto-approve"
+  allowedToolsStorage: "memory"
+
+llm:
+  provider: google
+  model: gemini-2.5-flash
+  apiKey: $GOOGLE_GENERATIVE_AI_API_KEY
+
+storage:
+  cache:
+    type: in-memory
+  database:
+    type: sqlite
+    path: .dexto/database/nano-banana-agent.db

package/dist/agents/podcast-agent/README.md

@@ -0,0 +1,168 @@
+# Advanced Podcast Generation Agent
+
+An AI agent for creating multi-speaker audio content using the Gemini TTS MCP server.
+
+## Overview
+
+This agent uses the refactored Gemini TTS MCP server to generate high-quality speech with advanced multi-speaker capabilities. It supports 30 prebuilt voices, natural language tone control, and can generate entire conversations with multiple speakers in a single request. The server now returns audio content that can be played directly in web interfaces.
+
+## Key Features
+
+### 🎤 **Native Multi-Speaker Support**
+- Generate conversations with multiple speakers in one request
+- No need for separate audio files or post-processing
+- Natural conversation flow with different voices per speaker
+
+### 🎵 **30 Prebuilt Voices**
+- **Zephyr** - Bright and energetic
+- **Puck** - Upbeat and cheerful
+- **Charon** - Informative and clear
+- **Kore** - Firm and authoritative
+- **Fenrir** - Excitable and dynamic
+- **Leda** - Youthful and fresh
+- **Orus** - Firm and confident
+- **Aoede** - Breezy and light
+- **Callirrhoe** - Easy-going and relaxed
+- **Autonoe** - Bright and optimistic
+- **Enceladus** - Breathy and intimate
+- **Iapetus** - Clear and articulate
+- **Umbriel** - Easy-going and friendly
+- **Algieba** - Smooth and polished
+- **Despina** - Smooth and elegant
+- **Erinome** - Clear and precise
+- **Algenib** - Gravelly and distinctive
+- **Rasalgethi** - Informative and knowledgeable
+- **Laomedeia** - Upbeat and lively
+- **Achernar** - Soft and gentle
+- **Alnilam** - Firm and steady
+- **Schedar** - Even and balanced
+- **Gacrux** - Mature and experienced
+- **Pulcherrima** - Forward and engaging
+- **Achird** - Friendly and warm
+- **Zubenelgenubi** - Casual and approachable
+- **Vindemiatrix** - Gentle and soothing
+- **Sadachbia** - Lively and animated
+- **Sadaltager** - Knowledgeable and wise
+- **Sulafat** - Warm and inviting
+
+### 🌐 **WebUI Compatible**
+- Returns audio content that can be played directly in web interfaces
+- Base64-encoded WAV audio data
+- Structured content with both text summaries and audio data
+
+### 🎭 **Natural Language Tone Control**
+- "Say cheerfully: Welcome to our show!"
+- "Speak in a formal tone: Welcome to our meeting"
+- "Use an excited voice: This is amazing news!"
+- "Speak slowly and clearly: This is important information"
+
+## Setup
+
+1. **Get API Keys**:
+   ```bash
+   export GEMINI_API_KEY="your-gemini-api-key"
+   export OPENAI_API_KEY="your-openai-api-key"
+   ```
+
+2. **Run the Agent**:
+   ```bash
+   dexto --mode web -a agents/podcast-agent/podcast-agent.yml
+   ```
+
+The agent will automatically install the Gemini TTS MCP server from npm when needed.
+
+## Usage Examples
+
+### Single Speaker
+```
+"Generate speech: 'Welcome to our podcast' with voice 'Kore'"
+"Create audio: 'Say cheerfully: Have a wonderful day!' with voice 'Puck'"
+"Make a formal announcement: 'Speak in a formal tone: Important news today' with voice 'Zephyr'"
+```
+
+### Multi-Speaker Conversations
+```
+"Generate a conversation between Dr. Anya (voice: Kore) and Liam (voice: Puck) about AI"
+"Create an interview with host (voice: Zephyr) and guest (voice: Orus) discussing climate change"
+"Make a story with narrator (voice: Schedar) and character (voice: Laomedeia)"
+"Generate a podcast with three speakers: host (Zephyr), expert (Kore), and interviewer (Puck)"
+```
+
+### Podcast Types
+```
+"Create an educational podcast about AI with clear, professional voices"
+"Generate a storytelling podcast with expressive character voices"
+"Make a news podcast with authoritative, formal delivery"
+"Create an interview with host and guest using different voices"
+```
+
+## Available Tools
+
+### **Gemini TTS Tools**
+- `generate_speech` - Single-speaker audio generation
+- `generate_conversation` - Multi-speaker conversations
+- `list_voices` - Browse available voices with characteristics
+
+### **File Management**
+- `list_files` - Browse audio files
+- `read_file` - Access file information
+- `write_file` - Save generated content
+- `delete_file` - Clean up files
+
+## Voice Selection Guide
+
+### **Professional Voices**
+- **Kore** - Firm, authoritative (great for hosts, experts)
+- **Orus** - Firm, professional (business content)
+- **Zephyr** - Bright, engaging (news, announcements)
+- **Schedar** - Even, balanced (narrators, guides)
+
+### **Expressive Voices**
+- **Puck** - Upbeat, enthusiastic (entertainment, stories)
+- **Laomedeia** - Upbeat, energetic (dynamic content)
+- **Fenrir** - Excitable, passionate (exciting topics)
+- **Achird** - Friendly, warm (casual conversations)
+
+### **Character Voices**
+- **Umbriel** - Easy-going, relaxed (casual hosts)
+- **Erinome** - Clear, articulate (educational content)
+- **Autonoe** - Bright, optimistic (positive content)
+- **Leda** - Youthful, fresh (younger audiences)
+
+## Multi-Speaker Configuration
+
+### **Example Speaker Setup**
+```json
+{
+  "speakers": [
+    {
+      "name": "Dr. Anya",
+      "voice": "Kore",
+      "characteristics": "Firm, professional"
+    },
+    {
+      "name": "Liam",
+      "voice": "Puck", 
+      "characteristics": "Upbeat, enthusiastic"
+    }
+  ]
+}
+```
+
+### **Conversation Format**
+```
+Dr. Anya: Welcome to our science podcast!
+Liam: Thanks for having me, Dr. Anya!
+Dr. Anya: Today we're discussing artificial intelligence.
+Liam: It's such an exciting field!
+```
+
+## Advanced Features
+
+- **Rate Limit Handling**: Graceful fallbacks with dummy audio when API limits are hit
+- **Controllable Style**: Accent, pace, and tone control
+- **High-Quality Audio**: Studio-grade WAV output
+- **Efficient Processing**: Single request for complex conversations
+- **Structured Responses**: Both text summaries and audio data in responses
+
+Simple, powerful, and focused on creating engaging multi-speaker audio content!