roast-ai 0.4.6 → 0.4.8

data/examples/tool_config_example/README.md

@@ -1,109 +0,0 @@
-# Tool Configuration Example
-
-This example demonstrates how to configure tools with specific settings in Roast workflows.
-
-## Overview
-
-Starting with this update, Roast supports configuring tools with specific settings directly in the workflow YAML file. This is particularly useful for tools like `Roast::Tools::Cmd` where you might want to restrict which commands can be executed.
-
-## Configuration Syntax
-
-Tools can be configured in two ways:
-
-### 1. Simple String Format (No Configuration)
-```yaml
-tools:
-  - Roast::Tools::ReadFile
-  - Roast::Tools::WriteFile
-  - Roast::Tools::Grep
-```
-
-### 2. Hash Format (With Configuration)
-```yaml
-tools:
-  - Roast::Tools::Cmd:
-      allowed_commands:
-        - ls
-        - pwd
-        - echo
-```
-
-### 3. Mixed Format
-You can mix both formats in the same workflow:
-
-```yaml
-tools:
-  - Roast::Tools::ReadFile
-  - Roast::Tools::Cmd:
-      allowed_commands:
-        - ls
-        - pwd
-        - ruby
-        - sed
-  - Roast::Tools::WriteFile
-  - Roast::Tools::SearchFile
-```
-
-## Example: Configuring Allowed Commands
-
-The `Roast::Tools::Cmd` tool now supports an `allowed_commands` configuration that restricts which commands can be executed:
-
-```yaml
-tools:
-  - Roast::Tools::Cmd:
-      allowed_commands:
-        - ls
-        - pwd
-        - echo
-        - cat
-        - ruby
-        - rake
-```
-
-### Enhanced Command Configuration with Descriptions
-
-You can also provide custom descriptions for commands to help the LLM understand their purpose:
-
-```yaml
-tools:
-  - Roast::Tools::Cmd:
-      allowed_commands:
-        - ls
-        - pwd
-        - name: echo
-          description: "echo command - output text to stdout, supports > for file redirection"
-        - name: cat
-          description: "cat command - display file contents, concatenate files, works with pipes"
-```
-
-This mixed format allows you to:
-- Use simple strings for commands with good default descriptions
-- Provide custom descriptions for commands that need more context
-- Help the LLM make better decisions about which command to use
-
-With this configuration:
-- ✅ `ls -la` will work
-- ✅ `echo "Hello World"` will work
-- ❌ `rm file.txt` will be rejected (not in allowed list)
-- ❌ `git status` will be rejected (not in allowed list)
-
-## Default Behavior
-
-If no configuration is provided for `Roast::Tools::Cmd`, it uses the default allowed commands:
-- pwd
-- find
-- ls
-- rake
-- ruby
-- dev
-- mkdir
-
-## Running the Example
-
-To run this example workflow:
-
-```bash
-bin/roast execute examples/tool_config_example/workflow.yml
-```
-
-The workflow will validate the tool configuration by executing various commands and demonstrating which ones are allowed and which are rejected based on the configuration.

data/examples/tool_config_example/example_step/prompt.md

@@ -1,42 +0,0 @@
-# Tool Configuration Validation
-
-Execute the following commands using the cmd tool:
-
-1. `ls -la`
-2. `pwd`
-3. `echo "Hello from configured commands!"`
-4. `git status`
-
-RESPONSE FORMAT
-You must respond in JSON format within <json> XML tags.
-
-<json>
-{
-  "commands": [
-    {
-      "command": "ls -la",
-      "exit_status": 0,
-      "output": "total 208\ndrwxr-xr-x@ 31 user  staff...",
-      "success": true
-    },
-    {
-      "command": "pwd",
-      "exit_status": 0,
-      "output": "/Users/user/project",
-      "success": true
-    },
-    {
-      "command": "echo \"Hello from configured commands!\"",
-      "exit_status": 0,
-      "output": "Hello from configured commands!",
-      "success": true
-    },
-    {
-      "command": "git status",
-      "exit_status": null,
-      "output": "Error: Command not allowed. Only commands starting with ls, pwd, echo, cat are permitted.",
-      "success": false
-    }
-  ]
-}
-</json>

data/examples/tool_config_example/workflow.yml

@@ -1,17 +0,0 @@
-name: Tool Configuration Example
-model: default
-tools:
-  - Roast::Tools::ReadFile
-  - Roast::Tools::Cmd:
-      allowed_commands:
-        - ls
-        - pwd
-        - name: echo
-          description: "echo command - output text to stdout, supports > for file redirection"
-        - name: cat
-          description: "cat command - display file contents, concatenate files, works with pipes"
-  - Roast::Tools::WriteFile
-
-steps:
-  - example_step
-

data/examples/user_input/README.md

@@ -1,90 +0,0 @@
-# User Input Example
-
-This example demonstrates how to use the `input` step type in Roast workflows to collect information from users during workflow execution.
-
-## Overview
-
-The `input` step type allows workflows to:
-- Collect text input from users
-- Ask yes/no questions (boolean)
-- Present multiple choice options
-- Securely collect passwords (hidden input)
-- Store collected values in workflow state for later use
-
-## Running the Example
-
-```bash
-# Run the interactive deployment workflow
-roast execute examples/user_input/workflow.yml
-
-# Run a simple survey workflow
-roast execute examples/user_input/survey_workflow.yml
-```
-
-## Input Step Configuration
-
-### Basic Text Input
-```yaml
-- input:
-    prompt: "Enter your name:"
-    name: user_name
-```
-
-### Boolean (Yes/No) Input
-```yaml
-- input:
-    prompt: "Do you want to continue?"
-    type: boolean
-    default: true
-    name: should_continue
-```
-
-### Choice Selection
-```yaml
-- input:
-    prompt: "Select environment:"
-    type: choice
-    options:
-      - development
-      - staging
-      - production
-    name: environment
-```
-
-### Password Input
-```yaml
-- input:
-    prompt: "Enter password:"
-    type: password
-    required: true
-    name: user_password
-```
-
-## Configuration Options
-
-- `prompt` (required): The question or message to display to the user
-- `name` (optional): Variable name to store the input value in workflow state
-- `type` (optional): Type of input - `text` (default), `boolean`, `choice`, or `password`
-- `required` (optional): Whether the input is required (default: false)
-- `default` (optional): Default value if user presses enter without input
-- `timeout` (optional): Timeout in seconds for user input
-- `options` (required for choice type): Array of options for choice selection
-
-## Accessing Input Values
-
-Input values stored with a `name` can be accessed in subsequent steps using interpolation:
-
-```yaml
-- input:
-    prompt: "Enter project name:"
-    name: project_name
-
-- prompt: "Creating project: #{state.project_name}"
-```
-
-## Non-TTY Environments
-
-When running in non-TTY environments (e.g., CI/CD pipelines), input steps will:
-- Use default values if provided
-- Fail if required inputs have no default
-- Skip optional inputs without defaults

data/examples/user_input/funny_name/create_backstory/prompt.md

@@ -1,10 +0,0 @@
-Create a hilarious and absurd backstory for someone named <%= workflow.output.user_name %> as a <%= workflow.output.genre %>.
-
-Make it funny, creative, and include:
-- A ridiculous origin story
-- An absurd special ability or talent related to their name
-- A nemesis with an equally silly name
-- Their greatest achievement (make it hilariously mundane yet epic)
-- A catchphrase that makes no sense
-
-Keep it fun and family-friendly! Format it as an entertaining narrative.

data/examples/user_input/funny_name/workflow.yml

@@ -1,26 +0,0 @@
-name: funny_name_backstory
-description: Create a humorous backstory based on your name
-model: anthropic:claude-3-5-sonnet
-
-steps:
-  # Collect user's name
-  - input:
-      prompt: "What's your name?"
-      name: user_name
-      required: true
-  
-  # Ask for preferences
-  - input:
-      prompt: "Pick a genre for your backstory:"
-      type: choice
-      options:
-        - "Epic Fantasy Adventure"
-        - "Cyberpunk Hacker"
-        - "Time-Traveling Detective"
-        - "Intergalactic Pizza Delivery"
-        - "Victorian-Era Vampire Hunter"
-        - "Professional Cat Whisperer"
-      name: genre
-  
-  # Generate the backstory
-  - create_backstory

data/examples/user_input/generate_summary/prompt.md

@@ -1,11 +0,0 @@
-Please generate a nicely formatted survey summary based on the following information:
-
-Survey Participant: <%= workflow.output.developer_name %>
-Usage Duration: <%= workflow.output.usage_duration %>
-Experience Rating: <%= workflow.output.experience_rating %>
-Primary Feature Used: <%= workflow.output.primary_feature %>
-Additional Feedback Provided: <%= workflow.output.user_feedback %>
-Contact Permission: <%= workflow.output.allow_contact %>
-Email (if provided): <%= workflow.output.user_email %>
-
-Format this as a professional survey summary report with proper headings and thank the participant for their time.

data/examples/user_input/simple_input_demo/workflow.yml

@@ -1,35 +0,0 @@
-name: simple_input_demo
-description: Simple demonstration of input step functionality
-model: gpt-4o
-
-steps:
-  # Text input
-  - input:
-      prompt: "What's your name?"
-      name: user_name
-      required: true
-  
-  - input:
-      prompt: "Are you enjoying Roast?"
-      type: boolean
-      default: true
-      name: enjoying_roast
-  
-  - input:
-      prompt: "What's your favorite programming language?"
-      type: choice
-      options:
-        - Ruby
-        - Python
-        - JavaScript
-        - Go
-        - Other
-      name: favorite_language
-  
-  - input:
-      prompt: "Create a secret password (won't be displayed):"
-      type: password
-      required: true
-      name: secret_password
-  
-  - "Summarize the following inputs: {{workflow.output}}"

data/examples/user_input/survey_workflow.yml

@@ -1,71 +0,0 @@
-name: developer_survey
-description: Collect developer feedback through an interactive survey
-model: anthropic:claude-3-5-sonnet
-
-steps:
-  - welcome_message
-  
-  # Basic information
-  - input:
-      prompt: "What's your name?"
-      name: developer_name
-      required: true
-  
-  - input:
-      prompt: "How long have you been using Roast? (e.g., '2 weeks', '3 months')"
-      name: usage_duration
-  
-  # Experience rating
-  - input:
-      prompt: "How would you rate your experience with Roast?"
-      type: choice
-      options:
-        - "⭐ Poor"
-        - "⭐⭐ Below Average"
-        - "⭐⭐⭐ Average"
-        - "⭐⭐⭐⭐ Good"
-        - "⭐⭐⭐⭐⭐ Excellent"
-      name: experience_rating
-      required: true
-  
-  # Feature usage
-  - input:
-      prompt: "Which Roast features do you use most? (select primary feature)"
-      type: choice
-      options:
-        - "AI-powered workflows"
-        - "File processing and manipulation"
-        - "Conditional execution (if/case)"
-        - "Iteration features (each/repeat)"
-        - "Tool integrations"
-        - "Other"
-      name: primary_feature
-  
-  # Feedback collection
-  - input:
-      prompt: "Would you like to provide additional feedback?"
-      type: boolean
-      default: true
-      name: wants_feedback
-  
-  - if: "{{workflow.output.wants_feedback}}"
-    then:
-      - input:
-          prompt: "Please share your feedback (press Enter twice when done):"
-          name: user_feedback
-      
-      - input:
-          prompt: "May we contact you about your feedback?"
-          type: boolean
-          default: false
-          name: allow_contact
-      
-      - if: "{{workflow.output.allow_contact}}"
-        then:
-          - input:
-              prompt: "Please enter your email:"
-              name: user_email
-              required: true
-  
-  # Generate summary
-  - generate_summary

data/examples/user_input/welcome_message/prompt.md

@@ -1,3 +0,0 @@
-Welcome to the Roast Developer Survey! 🎯
-
-You don't need to do anything here - just acknowledge this message and we'll proceed with collecting your feedback.

data/examples/user_input/workflow.yml

@@ -1,73 +0,0 @@
-name: interactive_deployment
-description: Interactive deployment workflow with user confirmations
-model: gpt-4o
-
-steps:
-  # Collect deployment information
-  - input:
-      prompt: "Which environment do you want to deploy to?"
-      name: environment
-      type: choice
-      options:
-        - development
-        - staging
-        - production
-      required: true
-  
-  - input:
-      prompt: "Enter the deployment tag/version:"
-      name: deploy_tag
-      required: true
-      default: "latest"
-  
-  # Show deployment plan
-  - bash:
-      command: |
-        echo "==================================="
-        echo "       DEPLOYMENT PLAN"
-        echo "==================================="
-        echo "Environment: {{workflow.output.environment}}"
-        echo "Version: {{workflow.output.deploy_tag}}"
-        echo "Timestamp: {{Date.today}}"
-        echo "==================================="
-  
-  # Confirm deployment
-  - input:
-      prompt: "Deploy {{workflow.output.deploy_tag}} to {{workflow.output.environment}}?"
-      type: boolean
-      default: false
-      name: confirm_deploy
-  
-  # Execute deployment if confirmed
-  - if: "{{workflow.output.confirm_deploy}}"
-    then:
-      - bash:
-          command: echo "🚀 Starting deployment to {{workflow.output.environment}}..."
-      
-      # Simulate deployment steps
-      - bash:
-          command: |
-            echo "🚀 Deploying version {{workflow.output.deploy_tag}} to {{workflow.output.environment}}"
-            echo "📦 Pulling Docker image: myapp:{{workflow.output.deploy_tag}}"
-            sleep 2
-            echo "🔄 Rolling out to {{workflow.output.environment}} cluster"
-            sleep 2
-            echo "✅ Deployment completed successfully!"
-      
-      # Post-deployment verification
-      - input:
-          prompt: "Run smoke tests?"
-          type: boolean
-          default: true
-          name: run_tests
-      
-      - if: "{{workflow.output.run_tests}}"
-        then:
-          - bash:
-              command: |
-                echo "🧪 Running smoke tests..."
-                sleep 1
-                echo "✅ All tests passed!"
-    else:
-      - bash:
-          command: echo "❌ Deployment cancelled by user."

data/examples/workflow_generator/README.md

@@ -1,27 +0,0 @@
-# Workflow Generator
-
-This workflow generates new Roast workflows based on user descriptions. It's the engine behind the "New from prompt" option in `roast init`.
-
-## How It Works
-
-The workflow generator takes a user description and workflow name, then:
-
-1. **Analyzes the request** - Understands what type of workflow is needed, what steps are required, and what tools should be used
-2. **Generates structure** - Creates a complete workflow configuration including YAML and step prompts
-3. **Creates files** - Writes all the necessary files and directories to disk
-
-## Usage
-
-This workflow is typically invoked automatically by the `roast init` command, but can also be run directly:
-
-```bash
-# Run the generator workflow
-roast execute examples/workflow_generator/workflow.yml
-```
-
-## Generated Output
-
-The workflow creates a new directory with:
-- `workflow.yml` - Main workflow configuration
-- `step_name/prompt.md` - Individual step prompts
-- `README.md` - Documentation for the generated workflow

data/examples/workflow_generator/analyze_user_request/prompt.md

@@ -1,34 +0,0 @@
-You are an assistant that analyzes user requests to understand what kind of workflow they want to create.
-
-Based on the user input from the previous step:
-<%= workflow.output["get_user_input"] %>
-
-Roast information from previous step:
-<%= workflow.output["info_from_roast"] %>
-
-First, explore existing workflow examples in the examples directory to understand common patterns and structures. Look for ones that may be related to the user's intention.
-
-Then analyze the user's request and determine:
-
-1. **Required Steps**: Break down the workflow into logical steps. Each step should be a discrete task that can be accomplished with an AI prompt.
-
-2. **Tools Needed**: What Roast tools will be needed? Base this on the actual tools you read from info provided above. 
-
-3. **Target Strategy**: Will this workflow:
-   - Process specific files (needs target configuration)
-   - Be targetless (works without specific input files)
-   - Use shell commands to find targets dynamically
-
-4. **Model Requirements**: Should this use a specific model, or is the default (gpt-4o-mini) sufficient?
-
-Respond with a structured analysis in this format:
-
-```
-STEPS: [list of 3-5 logical steps]
-TOOLS: [list of required tools]
-TARGET_STRATEGY: [targetless/files/dynamic]
-MODEL: [model recommendation]
-COMPLEXITY: [simple/moderate/complex]
-```
-
-Be specific and actionable in your analysis.

data/examples/workflow_generator/create_workflow_files/prompt.md

@@ -1,32 +0,0 @@
-You are an assistant that creates the actual workflow files in the filesystem.
-
-Based on the user input:
-<%= workflow.output["get_user_input"] %>
-
-And the generated workflow structure from the previous step:
-<%= workflow.output["analyze_user_request"] %>
-
-And info from roast:
-<%= workflow.output["info_from_roast"] %>
-
-Your task is to create all the necessary files and directories for the workflow.
-
-Extract the workflow name from the user input JSON and create the workflow in the current directory under that folder name.
-
-Steps to complete:
-
-1. **Create the main directory**: Use Cmd to create the "<%= workflow_name %>" directory
-2. **Create step directories**: Create subdirectories for each workflow step  
-3. **Create workflow.yml**: Write the main workflow configuration file
-4. **Create step prompt files**: Write each step's prompt.md file
-5. **Create README.md**: Generate a helpful README explaining the workflow
-
-When writing files, extract the content from the structured response and write each file separately.
-
-Important notes:
-- Make sure all directories exist before writing files to them
-- Follow the exact structure specified in the previous step
-- Include helpful comments in the workflow.yml file
-- Make the README.md informative and include usage instructions
-
-At the end, confirm that all files have been created by listing the directory structure.

data/examples/workflow_generator/get_user_input/prompt.md

@@ -1,14 +0,0 @@
-You need to collect user input for generating a new workflow.
-
-Step 1: Ask for the workflow description using ask_user tool with prompt: "What should your workflow do?"
-
-Step 2: Ask for the workflow name using ask_user tool with prompt: "Enter workflow directory name:"
-
-Step 3: Return the result in JSON format:
-
-<json>
-{
-  "user_description": "what the user wants the workflow to do", 
-  "workflow_name": "directory_name_provided_by_user"
-}
-</json>

data/examples/workflow_generator/info_from_roast.rb

@@ -1,22 +0,0 @@
-# frozen_string_literal: true
-
-class InfoFromRoast < Roast::Workflow::BaseStep
-  def call
-    examples_path = File.join(Roast::ROOT, "examples")
-    tools_path = File.join(Roast::ROOT, "lib", "roast", "tools")
-
-    # Get list of available tools
-    available_tools = Dir.entries(tools_path)
-      .select { |file| file.end_with?(".rb") }
-      .map { |file| file.gsub(".rb", "") }
-      .reject { |tool| tool == "." || tool == ".." }
-      .sort
-
-    {
-      examples_directory: examples_path,
-      tools_directory: tools_path,
-      available_tools: available_tools,
-      message: "Examples directory and available tools provided for analysis step",
-    }
-  end
-end

data/examples/workflow_generator/workflow.yml

@@ -1,34 +0,0 @@
-# Workflow Generator
-#
-# This workflow generates new Roast workflows based on user descriptions.
-# It gets user input, analyzes the request, generates an appropriate workflow structure,
-# and creates all necessary files in a new directory.
-
-name: Workflow Generator
-model: gpt-4o-mini
-
-tools:
-  - Roast::Tools::WriteFile
-  - Roast::Tools::ReadFile
-  - Roast::Tools::Cmd
-  - Roast::Tools::AskUser
-
-steps:
-  - get_user_input
-  - info_from_roast
-  - analyze_user_request
-  - create_workflow_files
-
-# Step configurations
-get_user_input:
-  print_response: false
-  json: true
-
-analyze_user_request:
-  print_response: true
-
-generate_workflow_structure:
-  print_response: true
-
-create_workflow_files:
-  print_response: false