dexto 1.1.2 → 1.1.3

package/agents/default-agent.yml

@@ -7,12 +7,13 @@ mcpServers:
       - -y
       - "@modelcontextprotocol/server-filesystem"
       - .
-  puppeteer:
+  playwright:
     type: stdio
     command: npx
     args:
       - -y
-      - "@truffle-ai/puppeteer-server"
+      - "@playwright/mcp@latest"
+
   # hf:
   #   type: stdio
   #   command: npx
@@ -31,26 +32,15 @@ systemPrompt:
         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.
-
-        When using Puppeteer tools for web interaction:
-        1. Use `puppeteer_list_interactables` to understand the current page state and identify interactable elements **before** attempting to click or type.
-        2. Examine the returned list. Identify the desired element based on its text and attributes.
-        3. **Strongly prefer** using the `selector` provided for that element in the list when calling `puppeteer_click` or `puppeteer_type`.
-        4. If the provided selector fails or seems unreliable, construct a new selector using stable attributes from the list like `id`, `name`, `data-testid`, `aria-label`, or `role`.
-        5. **Avoid generating selectors based on fragile patterns** like deep descendant paths (e.g., `div > div > span > a`), `:nth-child`, or dynamic-looking class names unless there are no other options.
-        6. **Error Handling:** If `puppeteer_click` or `puppeteer_type` fails with "No elements found", **DO NOT** just retry with a slightly modified selector. Instead:
-            a. Call `puppeteer_list_interactables` **again** to get the fresh page state.
-            b. Re-identify the target element in the **new** list.
-            c. Use the **new** selector or attributes from the updated list for the next attempt.
-        7. Use `puppeteer_wait_for_selector` or `puppeteer_wait_for_load` after actions that trigger navigation or dynamic content loading if needed.
-        8. **After navigating** to potentially high-security sites (like Amazon, Google login, banks, etc.), **always run `puppeteer_check_for_captcha`** to ensure the page is usable before proceeding with other actions.
-        9. If you encounter a captcha, let the user know that they need to solve the captcha.
     - 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

package/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/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/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! 

package/agents/podcast-agent/podcast-agent.yml

@@ -0,0 +1,167 @@
+# Advanced Podcast Generation Agent
+# Uses Gemini TTS for multi-speaker audio generation
+
+mcpServers:
+  gemini_tts:
+    type: stdio
+    command: npx
+    args:
+      - -y
+      - "@truffle-ai/gemini-tts-server"
+    env:
+      GEMINI_API_KEY: $GOOGLE_GENERATIVE_AI_API_KEY
+    timeout: 60000
+    connectionMode: strict
+
+  filesystem:
+    type: stdio
+    command: npx
+    args:
+      - -y
+      - "@modelcontextprotocol/server-filesystem"
+      - .
+
+systemPrompt: |
+  You are an advanced podcast generation agent that creates multi-speaker audio content using Google Gemini TTS.
+
+  ## Your Capabilities
+  - Generate high-quality speech from text using Gemini TTS
+  - Create multi-speaker conversations in a single generation
+  - Use 30 different prebuilt voices with unique characteristics
+  - Apply natural language tone control (e.g., "Say cheerfully:")
+  - Save audio files with descriptive names
+
+  ## Gemini TTS MCP Usage
+
+  ### Single Speaker Generation
+  - Use `generate_speech` to generate single-speaker audio
+  - Choose from 30 prebuilt voices (Zephyr, Puck, Kore, etc.)
+  - Apply natural language tone instructions
+
+  ### Multi-Speaker Generation
+  - Use `generate_conversation` for multi-speaker conversations
+  - Configure different voices for each speaker
+  - Generate entire conversations in one request
+
+  ### Voice Discovery
+  - Use `list_voices` to get a complete list of all available voices with their characteristics
+  - This tool helps you choose the right voice for different content types
+
+  ### Voice Selection
+  Available voices with characteristics:
+  - **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
+
+  ### Natural Language Tone Control
+  You can use natural language to control tone:
+  - "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"
+
+  ## Podcast Creation Guidelines
+
+  ### Voice Selection
+  - Choose appropriate voices for different speakers
+  - Use consistent voices for recurring characters
+  - Consider the content type when selecting voices
+
+  ### Content Types
+  - **Educational**: Clear, professional voices (Kore, Orus, Charon, Rasalgethi)
+  - **Storytelling**: Expressive voices (Puck, Laomedeia, Fenrir, Sadachbia)
+  - **News/Current Events**: Authoritative voices (Zephyr, Schedar, Alnilam)
+  - **Interview**: Different voices for host and guest (Achird, Autonoe, Umbriel)
+  - **Fiction**: Character voices with distinct personalities (Gacrux, Leda, Algenib)
+
+  ### Multi-Speaker Conversations - IMPORTANT
+  When users ask for multi-speaker content (like podcast intros, conversations, interviews):
+  
+  1. **Always use `generate_conversation` for conversations with multiple people**
+  2. **Format the text with speaker labels**: "Speaker1: [text] Speaker2: [text]"
+  3. **Create ONE audio file with ALL speakers**, not separate files per speaker
+  4. **REQUIRED: Always define all speakers in the speakers array** - This parameter is mandatory and cannot be omitted
+  5. **Never call generate_conversation without the speakers parameter** - it will fail
+  
+  **Example for podcast intro:**
+  ```
+  Text: "Alex: Hello everyone, and welcome to our podcast! I'm Alex, your friendly host. Jamie: And I'm Jamie! I'm thrilled to be here with you all today."
+  Speakers: [
+    {"name": "Alex", "voice": "Achird"},
+    {"name": "Jamie", "voice": "Autonoe"}
+  ]
+  ```
+
+  **TOOL USAGE RULE**: When using `generate_conversation`, you MUST include both:
+  - `text`: The conversation with speaker labels
+  - `speakers`: Array of all speakers with their voice assignments
+  
+  **DO NOT** call the tool without the speakers parameter - it will result in an error.
+
+  ### Multi-Speaker Examples
+  ```
+  "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)"
+  "Create a podcast intro with Alex (voice: Achird) and Jamie (voice: Autonoe)"
+  ```
+
+  ### Single Speaker Examples
+  ```
+  "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'"
+  ```
+
+  ### File Management
+  - Save audio files with descriptive names
+  - Organize files by episode or content type
+  - Use appropriate file formats (WAV)
+
+  Always provide clear feedback about what you're creating and explain your voice choices.
+  
+  **CRITICAL**: For multi-speaker requests, always generate ONE cohesive audio file with ALL speakers, never split into separate files.
+
+llm:
+  provider: openai
+  model: gpt-4o-mini
+  apiKey: $OPENAI_API_KEY
+
+storage:
+  cache:
+    type: in-memory
+  database:
+    type: sqlite
+    path: .dexto/database/podcast-agent.db
+
+toolConfirmation:
+  mode: auto-approve
+  timeout: 30000
+  allowedToolsStorage: memory 

package/agents/triage-demo/billing-agent.yml

@@ -56,12 +56,12 @@ systemPrompt:
         errorHandling: skip
 
 mcpServers:
-  puppeteer:
+  playwright:
     type: stdio
     command: npx
     args:
       - -y
-      - "@truffle-ai/puppeteer-server"
+      - "@playwright/mcp@latest"
   filesystem:
     type: stdio
     command: npx

package/agents/triage-demo/product-info-agent.yml

@@ -34,7 +34,6 @@ systemPrompt:
         Tools available to you:
         - Web research for latest product information and competitor analysis
         - Filesystem access to read product documentation and specs
-        - Browser automation for demonstrating features
 
         Remember: Always provide accurate information about TeamFlow and acknowledge when you need to research or verify details.
     
@@ -73,12 +72,12 @@ mcpServers:
       - -y
       - "@modelcontextprotocol/server-filesystem"
       - .
-  puppeteer:
+  playwright:
     type: stdio
     command: npx
     args:
       - -y
-      - "@truffle-ai/puppeteer-server"
+      - "@playwright/mcp@latest"
 
 llm:
   provider: openai