roast-ai 0.3.1 → 0.4.0

data/examples/iteration/update_fix_count/prompt.md

@@ -2,19 +2,19 @@ I'll update the count of fixes that have been successfully applied.
 
 Current fix count: 
 ```
-{{output.update_fix_count || 0}}
+<%= output.update_fix_count || 0 %>
 ```
 
 Verification result from the previous step:
 ```json
-{{output.verify_fix}}
+<%= output.verify_fix %>
 ```
 
 I'll increment the fix count if the verification was successful or partial, but not if it failed.
 
 ```javascript
-let currentCount = parseInt({{output.update_fix_count || 0}});
-let verificationStatus = "{{output.verify_fix.status}}";
+let currentCount = parseInt(<%= output.update_fix_count || 0 %>);
+let verificationStatus = "<%= output.verify_fix.status %>";
 
 if (verificationStatus === "success" || verificationStatus === "partial") {
   currentCount += 1;

data/examples/iteration/verify_fix/prompt.md

@@ -2,17 +2,17 @@ I'll verify that the fix implemented in the previous step correctly addresses th
 
 Here are the details of the issue that was fixed:
 ```json
-{{output.select_next_issue}}
+<%= output.select_next_issue %>
 ```
 
 And here is the implementation of the fix:
 ```json
-{{output.implement_fix}}
+<%= output.implement_fix %>
 ```
 
 Now I'll read the updated file to verify the changes:
 ```ruby
-{{read_file(output.select_next_issue.file_path)}}
+<%= read_file(output.select_next_issue.file_path) %>
 ```
 
 I'll evaluate the fix based on these criteria:

data/examples/mcp/README.md

@@ -44,7 +44,7 @@ tools:
         - --rm
         - ghcr.io/example/mcp-server
       env:
-        API_KEY: "{{env.API_KEY}}"
+        API_KEY: "{{ENV['API_KEY']}}"
       except:
         - dangerous_function
 ```
@@ -116,7 +116,7 @@ tools:
       command: npx
       args: ["-y", "@modelcontextprotocol/server-github"]
       env:
-        GITHUB_PERSONAL_ACCESS_TOKEN: "{{env.GITHUB_TOKEN}}"
+        GITHUB_PERSONAL_ACCESS_TOKEN: "{{ENV['GITHUB_TOKEN']}}"
       only:
         - search_repositories
         - get_issue
@@ -131,7 +131,7 @@ tools:
       command: npx
       args: ["-y", "@modelcontextprotocol/server-postgres"]
       env:
-        DATABASE_URL: "{{env.DATABASE_URL}}"
+        DATABASE_URL: "{{ENV['DATABASE_URL']}}"
       only:
         - query
         - list_tables

data/examples/mcp/analyze_changes/prompt.md

@@ -1,4 +1,4 @@
-For the file {{resource.target}}:
+For the file <%= resource.target %>:
 1. Read the file contents using read_file
 2. Use the Linter tool to analyze code quality
 3. Check for common issues:

data/examples/mcp/database_workflow.yml

@@ -12,7 +12,7 @@ tools:
         - "-y"
         - "@modelcontextprotocol/server-postgres"
       env:
-        DATABASE_URL: "{{env.DATABASE_URL}}"
+        DATABASE_URL: "{{ENV['DATABASE_URL']}}"
       only:
         - query
         - list_tables

data/examples/mcp/fetch_pr_context/prompt.md

@@ -1,4 +1,4 @@
-Using the GitHub tool, fetch details about PR #{{env.PR_NUMBER}}:
+Using the GitHub tool, fetch details about PR #<%= ENV['PR_NUMBER'] %>:
 1. Get the PR description and title
 2. List all changed files
 3. Identify the type of changes (feature, bugfix, refactor)

data/examples/mcp/github_workflow.yml

@@ -15,7 +15,7 @@ tools:
         - "-y"
         - "@modelcontextprotocol/server-github"
       env:
-        GITHUB_PERSONAL_ACCESS_TOKEN: "{{env.GITHUB_TOKEN}}"
+        GITHUB_PERSONAL_ACCESS_TOKEN: "{{ENV['GITHUB_TOKEN']}}"
       only:
         - search_repositories
         - get_repository

data/examples/mcp/post_review/prompt.md

@@ -1,3 +1,3 @@
-Using the GitHub tool, post the code review as a comment on PR #{{env.PR_NUMBER}}.
+Using the GitHub tool, post the code review as a comment on PR #<%= ENV['PR_NUMBER'] %>.
 Format the review in a friendly, constructive manner.
 Include specific line-by-line suggestions where appropriate.

data/examples/pre_post_processing/analyze_test_file/prompt.md

@@ -1,6 +1,6 @@
 # Analyze Test File
 
-Current test file: {{file}}
+Current test file: <%= file %>
 
 Please analyze this test file and identify:
 

data/examples/pre_post_processing/improve_test_coverage/prompt.md

@@ -1,6 +1,6 @@
 # Improve Test Coverage
 
-Based on the analysis of {{file}}, implement the following improvements:
+Based on the analysis of <%= file %>, implement the following improvements:
 
 1. **Add Missing Test Cases**: Write tests for uncovered code paths, edge cases, and error conditions
 2. **Improve Test Descriptions**: Make test names more descriptive and follow consistent naming conventions

data/examples/pre_post_processing/optimize_test_performance/prompt.md

@@ -1,6 +1,6 @@
 # Optimize Test Performance
 
-Optimize the performance of {{file}} by:
+Optimize the performance of <%= file %> by:
 
 1. **Reduce Setup Overhead**:
    - Move expensive operations out of individual test setup

data/examples/pre_post_processing/post_processing/aggregate_metrics/prompt.md

@@ -3,8 +3,8 @@
 Aggregate all the metrics collected during the workflow execution:
 
 Available data:
-- Pre-processing baseline metrics: {{pre_processing.gather_baseline_metrics}}
-- Results from all processed test files: {{output.targets}}
+- Pre-processing baseline metrics: <%= pre_processing.gather_baseline_metrics %>
+- Results from all processed test files: <%= output.targets %>
 
 Please calculate and provide:
 

data/examples/pre_post_processing/post_processing/generate_summary_report/prompt.md

@@ -9,7 +9,7 @@ Provide a high-level overview of the optimization results, key achievements, and
 
 ### Metrics Summary
 Include the aggregated metrics from the previous step:
-{{aggregate_metrics}}
+<%= aggregate_metrics %>
 
 ### Detailed Results by File
 For each processed test file, include:

data/examples/pre_post_processing/pre_processing/setup_test_environment/prompt.md

@@ -3,7 +3,7 @@
 Prepare the test environment for optimization. Please:
 
 1. Ensure all test dependencies are installed
-2. Create a backup branch for safety: `test-optimization-backup-{{timestamp}}`
+2. Create a backup branch for safety: `test-optimization-backup-<%= timestamp %>`
 3. Set up any necessary test databases or fixtures
 4. Configure test parallelization settings if available
 5. Clear any test caches that might affect benchmarking

data/examples/pre_post_processing/validate_changes/prompt.md

@@ -1,6 +1,6 @@
 # Validate Changes
 
-Validate the changes made to {{file}}:
+Validate the changes made to <%= file %>:
 
 1. **Run the updated tests** and ensure they all pass
 2. **Check coverage metrics** to verify improvements
@@ -11,7 +11,7 @@ Validate the changes made to {{file}}:
 Store the validation results in the workflow state:
 ```json
 {
-  "file": "{{file}}",
+  "file": "<%= file %>",
   "tests_passed": true,
   "coverage_before": 0.0,
   "coverage_after": 0.0,

data/examples/user_input/README.md

@@ -0,0 +1,90 @@
+# 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

@@ -0,0 +1,10 @@
+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

@@ -0,0 +1,26 @@
+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

@@ -0,0 +1,11 @@
+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

@@ -0,0 +1,35 @@
+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

@@ -0,0 +1,71 @@
+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

@@ -0,0 +1,3 @@
+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

@@ -0,0 +1,73 @@
+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/create_workflow_files/prompt.md

@@ -15,7 +15,7 @@ Extract the workflow name from the user input JSON and create the workflow in th
 
 Steps to complete:
 
-1. **Create the main directory**: Use Cmd to create the "{{ workflow_name }}" directory
+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

data/lib/roast/errors.rb

@@ -1,9 +1,11 @@
 # frozen_string_literal: true
 
 module Roast
-  # Custom error for API resource not found (404) responses
-  class ResourceNotFoundError < StandardError; end
+  module Errors
+    # Custom error for API resource not found (404) responses
+    class ResourceNotFoundError < StandardError; end
 
-  # Custom error for when API authentication fails
-  class AuthenticationError < StandardError; end
+    # Custom error for when API authentication fails
+    class AuthenticationError < StandardError; end
+  end
 end

data/lib/roast/helpers/function_caching_interceptor.rb

@@ -1,7 +1,5 @@
 # frozen_string_literal: true
 
-require "roast/helpers/logger"
-
 module Roast
   module Helpers
     # Intercepts function dispatching to add caching capabilities

data/lib/roast/helpers/logger.rb

@@ -1,54 +1,26 @@
 # frozen_string_literal: true
 
-require "logger"
-require "forwardable"
-
 module Roast
   module Helpers
     # Central logger for the Roast application
     class Logger
-      extend Forwardable
       VALID_LOG_LEVELS = ["DEBUG", "INFO", "WARN", "ERROR", "FATAL"].freeze
 
-      attr_reader :logger, :log_level
-
-      # Delegate info and warn methods to the underlying logger
-      def_delegators :logger, :info, :warn
-
-      # Create a specialized debug method that ensures proper functionality
-      def debug(message)
-        logger.debug(message)
-      end
-
-      def error(message)
-        # Add any custom error handling logic here
-        logger.error(message)
-      end
-
-      def fatal(message)
-        # Add any custom fatal error handling logic here
-        logger.fatal(message)
-      end
-
-      def initialize(stdout: $stdout, log_level: ENV["ROAST_LOG_LEVEL"] || "INFO")
-        @log_level = validate_log_level(log_level)
-        @logger = create_logger(stdout)
-      end
+      delegate_missing_to :@logger
 
-      def log_level=(level)
-        @log_level = validate_log_level(level)
-        logger.level = ::Logger.const_get(@log_level)
-      end
+      attr_reader :logger
 
       class << self
-        extend Forwardable
+        delegate_missing_to :instance
 
         def instance
           @instance ||= new
         end
 
-        # Delegate logging methods to the singleton instance
-        def_delegators :instance, :debug, :info, :warn, :error, :fatal
+        # Override Kernel#warn to ensure proper delegation
+        def warn(*args)
+          instance.warn(*args)
+        end
 
         # For testing purposes
         def reset
@@ -58,6 +30,11 @@ module Roast
 
       private
 
+      def initialize(stdout: $stdout, log_level: ENV["ROAST_LOG_LEVEL"] || "INFO")
+        @log_level = validate_log_level(log_level)
+        @logger = create_logger(stdout)
+      end
+
       def validate_log_level(level)
         level_str = level.to_s.upcase
         unless VALID_LOG_LEVELS.include?(level_str)

data/lib/roast/helpers/minitest_coverage_runner.rb

@@ -2,7 +2,6 @@
 
 require "coverage"
 require "minitest"
-require "roast/helpers/logger"
 
 # Disable the built-in `at_exit` hook for Minitest before anything else
 module Minitest

data/lib/roast/helpers/prompt_loader.rb

@@ -1,7 +1,5 @@
 # frozen_string_literal: true
 
-require "erb"
-
 module Roast
   module Helpers
     class PromptLoader

data/lib/roast/resources/api_resource.rb

@@ -1,9 +1,5 @@
 # frozen_string_literal: true
 
-require "json"
-require "net/http"
-require "uri"
-
 module Roast
   module Resources
     # Resource implementation for API endpoints using Fetch API-style format

data/lib/roast/resources/url_resource.rb

@@ -1,8 +1,5 @@
 # frozen_string_literal: true
 
-require "net/http"
-require "uri"
-
 module Roast
   module Resources
     # Resource implementation for URLs