roast-ai 0.4.7 → 0.4.9

data/examples/shared_config/README.md

@@ -1,52 +0,0 @@
-# Shared Configuration Example
-
-This example demonstrates how to use `shared.yml` to define common configuration anchors that can be referenced across multiple workflow files.
-
-## Structure
-
-```
-├── shared.yml                      # Common configuration anchors
-└── example_with_shared_config/
-    └── workflow.yml               # Workflow using shared anchors
-```
-
-## How it works
-
-1. When loading a workflow file, Roast checks if `shared.yml` exists one level above the workflow directory
-2. If found, it loads `shared.yml` first, then the workflow file
-3. This allows YAML anchors defined in `shared.yml` to be referenced in workflow files
-
-## Example Usage
-
-In `shared.yml`:
-```yaml
-standard_tools: &standard_tools
-  - Roast::Tools::Grep
-  - Roast::Tools::ReadFile
-  - Roast::Tools::WriteFile
-  - Roast::Tools::SearchFile
-
-mirage: &mirage '$(echo "Oh my god. Its a mirage")'
-```
-
-In your workflow:
-```yaml
-name: Example with shared config
-tools: *standard_tools  # Reference the standard tools from shared.yml
-
-steps:
-  - *mirage  # Reference a shared step definition
-  - sabotage: '$(echo "Im tellin yall, its sabotage")'
-```
-
-## Running the Example
-
-```bash
-# Run the workflow that uses shared configuration
-roast execute examples/shared_config/example_with_shared_config/workflow.yml
-```
-
-The workflow will:
-1. Load the shared configuration from `shared.yml`
-2. Apply the referenced tools and steps
-3. Execute the workflow with the merged configuration

data/examples/shared_config/example_with_shared_config/workflow.yml

@@ -1,6 +0,0 @@
-name: Example with shared config
-tools: *standard_tools
-
-steps:
-  - *mirage
-  - sabotage: '$(echo "Im tellin yall, its sabotage")'

data/examples/shared_config/shared.yml

@@ -1,7 +0,0 @@
-standard_tools: &standard_tools
-  - Roast::Tools::Grep
-  - Roast::Tools::ReadFile
-  - Roast::Tools::WriteFile
-  - Roast::Tools::SearchFile
-
-mirage: &mirage '$(echo "Oh my god. Its a mirage")'

data/examples/single_target_prepost/README.md

@@ -1,36 +0,0 @@
-# Single Target with Pre/Post Processing Example
-
-This example demonstrates how pre/post processing works with single-target workflows. Even when analyzing just one file, you can use pre-processing to gather context and post-processing to format results.
-
-## Features Demonstrated
-
-1. **Pre-processing for context gathering** - Analyze dependencies before the main workflow
-2. **Single-target analysis** - Focus on one specific file
-3. **Post-processing with output template** - Custom formatting of the final report
-
-## Running the Example
-
-```bash
-roast workflow.yml
-```
-
-This will:
-1. Run pre-processing to gather dependencies and context
-2. Analyze the single target file (src/main.rb)
-3. Apply the post-processing template to format the output
-
-## Output Template
-
-The `post_processing/output.txt` template demonstrates how to:
-- Access pre-processing results with `<%= pre_processing[:step_name] %>`
-- Iterate over target results (even for single targets)
-- Include post-processing step outputs
-- Format everything into a professional report
-
-## Use Cases
-
-This pattern is ideal for:
-- Deep analysis of critical files
-- Security audits of specific components
-- Performance profiling of key modules
-- Generating documentation for important classes

data/examples/single_target_prepost/post_processing/output.txt

@@ -1,27 +0,0 @@
-=== Code Analysis Report ===
-Generated: <%= Time.now.strftime("%Y-%m-%d %H:%M:%S") %>
-
-## Dependencies & Context
-<%= pre_processing.gather_dependencies %>
-
-## Target File Analysis
-<% targets.each do |file, target| %>
-File: <%= file %>
-
-### Code Quality
-<%= target.output.analyze_code_quality %>
-
-### Identified Improvements
-<%= target.output.identify_improvements %>
-
-### Recommendations
-<%= target.output.generate_recommendations %>
-<% end %>
-
-## Summary
-<%= output.summarize_findings %>
-
-## Action Items
-<%= output.create_action_items %>
-
-=== End of Report ===

data/examples/single_target_prepost/pre_processing/gather_dependencies/prompt.md

@@ -1,11 +0,0 @@
-# Gather Dependencies
-
-Analyze the project structure to understand the dependencies and context for <%= file %>.
-
-Tasks:
-1. List all files that import or depend on the target file
-2. Identify the key modules and classes used
-3. Note any external dependencies or libraries
-4. Summarize the architectural context
-
-Provide a structured summary that will help with the main analysis.

data/examples/single_target_prepost/workflow.yml

@@ -1,20 +0,0 @@
-name: analyze_codebase
-description: Analyze a single codebase with pre/post processing support
-model: gpt-4o
-target: "src/main.rb"
-
-# Pre-processing: Gather context before analyzing the main file
-pre_processing:
-  - gather_dependencies
-  - setup_analysis_tools
-
-# Main workflow: Analyze the target file
-steps:
-  - analyze_code_quality
-  - identify_improvements
-  - generate_recommendations
-
-# Post-processing: Generate final report
-post_processing:
-  - summarize_findings
-  - create_action_items

data/examples/smart_coercion_defaults/README.md

@@ -1,65 +0,0 @@
-# Smart Coercion Defaults
-
-This example demonstrates how Roast applies intelligent defaults for boolean coercion based on the type of expression being evaluated.
-
-## Default Coercion Rules
-
-When a step is used in a boolean context (like `if`, `unless`, or `until` conditions) and no explicit `coerce_to` is specified, Roast applies these smart defaults:
-
-1. **Ruby Expressions** (`{{expression}}`) → Regular boolean coercion (`!!value`)
-   - `nil` and `false` are falsy
-   - Everything else is truthy (including 0, empty arrays, etc.)
-
-2. **Bash Commands** (`$(command)`) → Exit code interpretation
-   - Exit code 0 = true (success)
-   - Non-zero exit code = false (failure)
-
-3. **Prompt/Step Names** → LLM boolean interpretation
-   - Analyzes natural language responses for yes/no intent
-   - "Yes", "True", "Affirmative" → true
-   - "No", "False", "Negative" → false
-
-4. **Non-string Values** → Regular boolean coercion
-
-## Examples
-
-### Ruby Expression (Regular Boolean)
-```yaml
-- repeat:
-    until: "{{counter >= 5}}"  # Uses !! coercion
-    steps:
-      - increment: counter
-```
-
-### Bash Command (Exit Code)
-```yaml
-- repeat:
-    until: "$(test -f /tmp/done)"  # True when file exists (exit 0)
-    steps:
-      - wait: 1
-```
-
-### Prompt Response (LLM Boolean)
-```yaml
-- if: "Should we continue?"  # Interprets "Yes, let's continue" as true
-  then:
-    - proceed: "Continuing..."
-```
-
-## Overriding Defaults
-
-You can always override the default coercion by specifying `coerce_to` directly in the step:
-
-```yaml
-- each: "get_items"
-  as: "item"
-  coerce_to: iterable  # Override default to split into array
-  steps:
-    - process: "{{item}}"
-```
-
-## Supported Coercion Types
-
-- `boolean` - Standard Ruby truthiness (!! operator)
-- `llm_boolean` - Natural language yes/no interpretation
-- `iterable` - Convert to array (splits strings on newlines)

data/examples/smart_coercion_defaults/workflow.yml

@@ -1,44 +0,0 @@
-name: Smart Coercion Defaults Demo
-description: Demonstrates how different step types get smart boolean coercion defaults
-
-steps:
-  # Example 1: Ruby expressions default to regular boolean coercion
-  - set_counter: 
-      value: 3
-  
-  - repeat:
-      until: "{{counter >= 5}}"  # Ruby expression defaults to boolean
-      steps:
-        - increment_counter: 
-            value: "{{counter + 1}}"
-        - log: "Counter is now {{counter}}"
-  
-  # Example 2: Bash commands default to exit code interpretation
-  - check_file_exists:
-      repeat:
-        until: "$(ls /tmp/important_file 2>/dev/null)"  # Bash command defaults to exit code
-        max_iterations: 3
-        steps:
-          - create_file: "$(mkdir -p /tmp && touch /tmp/important_file)"
-          - log: "Waiting for file to exist..."
-  
-  # Example 3: Prompt/step names default to LLM boolean interpretation
-  - ask_user_ready:
-      prompt: "Are you ready to continue? Please respond yes or no."
-  
-  - conditional:
-      if: "ask_user_ready"  # Step name defaults to llm_boolean
-      then:
-        - proceed: "Great! Let's continue..."
-      else:
-        - wait: "Okay, take your time."
-  
-  # Example 4: Explicit coerce_to overrides smart defaults
-  - get_items:
-      prompt: "List three fruits, one per line"
-  
-  - each: "get_items"
-    as: "fruit"
-    coerce_to: iterable  # Override default llm_boolean to iterable
-    steps:
-      - process_fruit: "Processing {{fruit}}"

data/examples/step_configuration/README.md

@@ -1,84 +0,0 @@
-# Step Configuration Example
-
-This example demonstrates how to configure various step types in Roast workflows, including:
-- Inline prompts
-- Iterator steps (each/repeat)
-- Regular steps
-
-## Configuration Options
-
-All step types support the following configuration options:
-
-- `model`: The AI model to use (e.g., "gpt-4o", "claude-3-opus")
-- `print_response`: Whether to print the response to stdout (true/false)
-- `json`: Whether to expect a JSON response (true/false)
-- `params`: Additional parameters to pass to the model (e.g., temperature, max_tokens)
-- `coerce_to`: How to convert the step result (options: "boolean", "llm_boolean", "iterable")
-
-## Configuration Precedence
-
-1. **Step-specific configuration** takes highest precedence
-2. **Global configuration** (defined at the workflow level) applies to all steps without specific configuration
-3. **Default values** are used when no configuration is provided
-
-## Inline Prompt Configuration
-
-Inline prompts can be configured in two ways:
-
-### As a top-level key:
-```yaml
-analyze the code:
-  model: gpt-4o
-  print_response: true
-```
-
-### Inline in the steps array:
-```yaml
-steps:
-  - suggest improvements:
-      model: claude-3-opus
-      params:
-        temperature: 0.9
-```
-
-## Iterator Configuration
-
-Both `each` and `repeat` steps support configuration:
-
-```yaml
-each:
-  each: "{{files}}"
-  as: file
-  model: gpt-3.5-turbo
-  steps:
-    - process {{file}}
-
-repeat:
-  repeat: true
-  until: "{{done}}"
-  model: gpt-4o
-  print_response: true
-  steps:
-    - check status
-```
-
-## Coercion Types
-
-The `coerce_to` option allows you to convert step results to specific types:
-
-- **`boolean`**: Converts any value to true/false (nil, false, empty string → false; everything else → true)
-- **`llm_boolean`**: Interprets natural language responses as boolean (e.g., "Yes", "Definitely!" → true; "No", "Not yet" → false)
-- **`iterable`**: Ensures the result can be iterated over (splits strings by newlines if needed)
-
-This is particularly useful when:
-- Using steps in conditional contexts (if/unless)
-- Using steps as conditions in repeat loops
-- Processing step results in each loops
-
-## Running the Example
-
-```bash
-bin/roast examples/step_configuration/workflow.yml
-```
-
-Note: This example is for demonstration purposes and shows the configuration syntax. You'll need to adapt it to your specific use case with appropriate prompts and logic.

data/examples/step_configuration/workflow.yml

@@ -1,57 +0,0 @@
-name: Step Configuration Example
-description: Demonstrates how to configure various step types including inline prompts, iterators, and regular steps
-
-# Global configuration that applies to all steps
-model: openai/gpt-4o-mini
-
-# Configuration for specific steps
-summarize the code:
-  model: claude-3-opus  # Override global model
-  print_response: true # Print the response
-  json: false          # Don't expect JSON response
-  params:
-    temperature: 0.7   # Custom temperature
-
-analyze complexity:
-  model: gpt-4o
-  json: true           # Expect JSON response
-  params:
-    temperature: 0.2   # Lower temperature for more consistent analysis
-
-# Iterator step configuration
-each:
-  each: "{{files}}"
-  as: file
-  model: gpt-3.5-turbo # Use a faster model for iteration
-  steps:
-    - process {{file}}
-
-repeat:
-  repeat: true
-  until: "are all tests passing"  # This will be evaluated as a step
-  max_iterations: 5
-  model: gpt-4o
-  print_response: true
-  coerce_to: llm_boolean  # Interpret natural language response as boolean
-  steps:
-    - run tests
-    - fix failing tests
-
-# Step used in boolean context
-are all tests passing:
-  model: gpt-4o
-  coerce_to: llm_boolean  # Convert "Yes, all tests are passing!" to true
-  params:
-    temperature: 0.2
-
-# Steps can mix configured and unconfigured inline prompts
-steps:
-  - list all source files           # Uses global configuration
-  - summarize the code              # Uses step-specific configuration
-  - analyze complexity              # Uses step-specific configuration
-  - suggest improvements:           # Step-specific configuration inline
-      model: claude-3-opus
-      params:
-        temperature: 0.9
-  - each                           # Iterator with configuration
-  - repeat                         # Iterator with configuration

data/examples/swarm_example.yml

@@ -1,25 +0,0 @@
-name: Swarm Example Workflow
-
-# Example workflow demonstrating Roast's integration with Claude Swarm
-# The Swarm tool is available to the LLM, which can choose to use it when appropriate
-
-tools:
-  - Roast::Tools::Swarm:
-      path: ".swarm.yml"  # Optional - will use default locations if not specified
-
-steps:
-  - orchestrate_refactoring: |
-      Help me refactor this codebase for better performance. Coordinate multiple 
-      Claude agents using the swarm configuration to:
-      1. Analyze the current code structure
-      2. Identify performance bottlenecks
-      3. Implement optimizations
-      4. Ensure backward compatibility
-      
-  - specialized_analysis: |
-      Now use the specialized swarm configuration at ./specialized-swarm.yml to run 
-      a comprehensive code analysis that includes:
-      - Architecture review
-      - Security audit  
-      - Documentation generation
-      - Test coverage analysis

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
-