roast-ai 0.1.6 → 0.2.0

data/examples/iteration/generate_recommendations/prompt.md

@@ -0,0 +1,21 @@
+Based on the analysis of complexity for file {{current_file}}, I'll generate specific recommendations for improving code quality.
+
+I'll use the complexity analysis from the previous step:
+```json
+{{output.analyze_complexity}}
+```
+
+For each identified issue, I'll provide detailed, actionable recommendations including:
+
+1. What specific changes should be made
+2. How the change improves the code
+3. Sample code snippets demonstrating the improvement
+4. An estimate of effort required (low, medium, high)
+5. Priority level for implementation
+
+I'll organize these recommendations to address:
+- Most critical issues first
+- Quick wins that provide significant value for minimal effort
+- Long-term architectural improvements
+
+My recommendations will follow Ruby best practices, adhere to common style guides, and consider maintainability, readability, and performance. 

data/examples/iteration/generate_report/prompt.md

@@ -0,0 +1,129 @@
+# Code Quality Improvement Report
+
+## Summary of Analysis and Improvements
+
+I've analyzed {{output.get_files_to_analyze.split('\n').length}} Ruby files for code quality issues and made targeted improvements.
+
+### Files Analyzed
+
+```
+{{output.get_files_to_analyze}}
+```
+
+### Issues Identified
+
+Total issues identified: {{output.prioritize_issues.total_issues}}
+
+Issues by severity:
+- High: {{output.prioritize_issues.high_severity || 0}}
+- Medium: {{output.prioritize_issues.medium_severity || 0}}
+- Low: {{output.prioritize_issues.low_severity || 0}}
+
+Issues by type:
+- Complexity: {{output.prioritize_issues.complexity_issues || 0}}
+- Maintainability: {{output.prioritize_issues.maintainability_issues || 0}}
+- Performance: {{output.prioritize_issues.performance_issues || 0}}
+- Style: {{output.prioritize_issues.style_issues || 0}}
+
+### Improvements Made
+
+Number of fixes applied: {{output.update_fix_count.fixes_applied || 0}}
+
+{{#if output.update_fix_count.fixes_applied > 0}}
+Fixes by type:
+{{#each output.fix_summary}}
+- {{this.type}}: {{this.count}} ({{this.percentage}}% of total)
+{{/each}}
+
+Top files improved:
+{{#each output.file_improvements}}
+- {{this.file}}: {{this.issues_fixed}} issues fixed
+{{/each}}
+{{else}}
+No fixes were applied during this run.
+{{/if}}
+
+## Detailed Fix List
+
+{{#if output.update_fix_count.fixes_applied > 0}}
+{{#each output.fixes_applied}}
+### Fix #{{@index + 1}}: {{this.issue.type}} in {{this.issue.file_path}}
+
+**Issue**: {{this.issue.description}}  
+**Location**: {{this.issue.location}}  
+**Severity**: {{this.issue.severity}}  
+
+**Solution Applied**: {{this.fix_description}}
+
+```diff
+{{this.diff}}
+```
+
+**Verification**: {{#if this.verification.success}}✅ Successful{{else}}❌ Failed: {{this.verification.reason}}{{/if}}
+
+{{/each}}
+{{else}}
+No fixes were applied during this run.
+{{/if}}
+
+## Recommendations for Future Improvements
+
+Based on the remaining issues, here are the top recommendations for improving code quality:
+
+{{#each output.top_recommendations}}
+{{@index + 1}}. **{{this.title}}**  
+   {{this.description}}  
+   Affected files: {{this.affected_files}}
+{{/each}}
+
+## Conclusion
+
+This automated code quality improvement run has {{#if output.update_fix_count.fixes_applied > 0}}successfully addressed {{output.update_fix_count.fixes_applied}} issues{{else}}identified issues but did not apply any fixes{{/if}}. The remaining issues should be reviewed and addressed as part of ongoing code maintenance.
+
+I'll generate a comprehensive summary report of all the code quality improvements made during this workflow.
+
+Total number of fixes applied:
+```
+{{output.update_fix_count.fixes_applied || 0}}
+```
+
+I'll analyze the following data to create the report:
+1. Original list of issues identified:
+```json
+{{output.prioritize_issues}}
+```
+
+2. Issues that were addressed:
+```json
+{{outputs_of.select_next_issue}}
+```
+
+3. Implementation and verification details:
+```json
+{{outputs_of.implement_fix}}
+{{outputs_of.verify_fix}}
+```
+
+The report will include:
+
+1. **Executive Summary**
+   - Total files analyzed
+   - Total issues identified
+   - Issues fixed vs. remaining
+   - Most common issue types
+   
+2. **Detailed Analysis by File**
+   - Issues fixed per file
+   - Before/after code quality assessment
+   
+3. **Implementation Details**
+   - Description of each fix
+   - Impact on code quality
+   - Verification results
+   
+4. **Recommendations**
+   - Remaining high-priority issues
+   - Suggested next steps
+   - Long-term code quality improvement suggestions
+
+This report provides a comprehensive overview of the code quality improvements made and serves as documentation for the changes implemented.

data/examples/iteration/implement_fix/prompt.md

@@ -0,0 +1,25 @@
+I'll implement the fix for the issue selected in the previous step.
+
+Here is the issue to fix:
+```json
+{{output.select_next_issue}}
+```
+
+First, I'll read the current file content to understand the context:
+
+```ruby
+{{read_file(output.select_next_issue.file_path)}}
+```
+
+Based on the issue description and the recommended changes, I'll implement a fix that:
+1. Addresses the specific issue identified
+2. Follows Ruby best practices and style conventions
+3. Is minimal and focused (changes only what's necessary)
+4. Maintains or improves the existing functionality
+
+I'll use the update_files tool to apply the changes. For each change, I'll provide:
+1. The file path
+2. The changes to make
+3. A detailed explanation of what was changed and why
+
+After implementing the fix, I'll return a summary of the changes made.

data/examples/iteration/prioritize_issues/prompt.md

@@ -0,0 +1,24 @@
+I'll analyze all the recommendations I've generated across multiple files and prioritize them according to:
+
+1. Severity of the issues
+2. Complexity of implementation
+3. Impact on code quality and maintainability
+4. Dependencies between issues
+
+Let me review all the recommendations collected so far:
+
+```json
+{{outputs_of.generate_recommendations}}
+```
+
+I'll create a comprehensive prioritized list of all issues across files, combining similar issues where appropriate. The prioritized list will include:
+
+1. Issue ID
+2. File path
+3. Issue description 
+4. Severity (High, Medium, Low)
+5. Implementation difficulty (Easy, Medium, Hard)
+6. Priority score (calculated from severity and difficulty)
+7. Dependencies (if any)
+
+This prioritized list will guide our approach to addressing the most important issues first, while being mindful of dependencies between issues. 

data/examples/iteration/prompts/analyze_file.md

@@ -0,0 +1,28 @@
+# Ruby File Method Analysis
+
+You are a code analyzer focusing on analyzing Ruby files to count the number of methods defined.
+
+## Input
+- File path: {{ file_path }}
+- File content:
+```ruby
+{{ tools.read_file.content(file_path) }}
+```
+
+## Task
+1. Analyze the Ruby file content
+2. Count the number of methods defined in the file (including class methods, instance methods, and module methods)
+3. Return a JSON object with:
+   - file_name: The basename of the file
+   - method_count: The number of methods found
+   - method_names: An array of method names found in the file
+
+## Response Format
+Return a JSON object with the following structure:
+```json
+{
+  "file_name": "base_step.rb",
+  "method_count": 5,
+  "method_names": ["initialize", "call", "validate", "execute", "helper_method"]
+}
+```

data/examples/iteration/prompts/generate_summary.md

@@ -0,0 +1,24 @@
+# Generate Method Analysis Summary
+
+You are a report generator responsible for summarizing the method analysis results.
+
+## Input
+- Report data: {{ report_data }}
+
+## Task
+1. Parse the report data as JSON
+2. Create a summary of the analysis results including:
+   - Total number of files analyzed
+   - Total number of methods found
+   - Average number of methods per file
+   - File with the most methods
+   - File with the fewest methods
+3. Generate a formatted summary text
+
+## Response Format
+Return a JSON object with the following structure:
+```json
+{
+  "summary": "## Ruby Method Analysis Summary\n\nAnalyzed 10 Ruby files in the workflow directory.\n- Total methods found: 45\n- Average methods per file: 4.5\n- Most methods: base_workflow.rb (12 methods)\n- Fewest methods: state_repository.rb (1 method)\n\n### Top 3 Files by Method Count\n1. base_workflow.rb: 12 methods\n2. configuration.rb: 8 methods\n3. workflow_executor.rb: 7 methods\n"
+}
+```

data/examples/iteration/prompts/update_report.md

@@ -0,0 +1,29 @@
+# Update Method Count Report
+
+You are a data updater responsible for adding analysis results to a report.
+
+## Input
+- File path: {{ file_path }}
+- Method count: {{ method_count }}
+- Current report data: {{ current_report }}
+
+## Task
+1. Parse the current report data as JSON
+2. Add the new file analysis results to the report's "results" array
+3. Increment the "files_analyzed" counter by 1
+4. Add the method count to the "total_methods" counter
+5. Return the updated JSON report
+
+## Response Format
+Return a JSON object with the updated report structure:
+```json
+{
+  "files_analyzed": 10,
+  "total_methods": 45,
+  "results": [
+    {"file_path": "file1.rb", "method_count": 5, "method_names": ["method1", "method2", ...]},
+    {"file_path": "file2.rb", "method_count": 3, "method_names": ["methodA", "methodB", ...]},
+    ...
+  ]
+}
+```

data/examples/iteration/prompts/write_report.md

@@ -0,0 +1,22 @@
+# Write Method Analysis Report
+
+You are responsible for creating a formatted report file based on the analysis results.
+
+## Input
+- Report data: {{ report_data }}
+- Summary: {{ summary }}
+
+## Task
+1. Generate a Markdown report that includes:
+   - The summary information
+   - A detailed table of all files analyzed, with their method counts and method names
+2. Format the report in a clean, readable manner
+
+## Response Format
+Return a JSON object with the following structure:
+```json
+{
+  "report_content": "# Ruby Method Analysis Report\n\n{{ summary }}\n\n## Detailed Results\n\n| File | Method Count | Methods |\n|------|--------------|--------|\n| file1.rb | 5 | method1, method2, ... |\n| file2.rb | 3 | methodA, methodB, ... |\n...",
+  "report_file_path": "method_analysis_report.md"
+}
+```

data/examples/iteration/read_file/prompt.md

@@ -0,0 +1,9 @@
+I'll analyze the Ruby file at: {{current_file}}
+
+First, let me read the content of this file.
+
+```ruby
+{{read_file current_file}}
+```
+
+I'll store this content for further analysis in the next steps.

data/examples/iteration/select_next_issue/prompt.md

@@ -0,0 +1,25 @@
+I'll select the next highest priority issue to fix from our prioritized list.
+
+Here is the current prioritized list of issues:
+```json
+{{output.prioritize_issues}}
+```
+
+And here is the count of fixes we've already applied:
+```
+{{output.update_fix_count || '0'}}
+```
+
+I'll select the highest priority issue that hasn't yet been addressed. I'll consider:
+
+1. The priority score from our previous analysis
+2. Dependencies between issues (ensuring prerequisites are addressed first)
+3. Logical grouping (addressing related issues in the same file together)
+
+If there are no issues left to fix, I'll indicate this with `{"no_issues_left": true}`.
+
+For the selected issue, I'll return:
+1. The issue details
+2. The file path to modify
+3. A clear description of the changes needed
+4. Any context needed for implementation

data/examples/iteration/simple_workflow.md

@@ -0,0 +1,39 @@
+# Simple Iteration Workflow Example
+
+This example demonstrates how to use both the `each` and `repeat` iteration constructs in Roast workflows.
+
+## Workflow Description
+
+The workflow analyzes Ruby files in the `lib/roast/workflow` directory and counts the number of methods defined in each file. The process follows these steps:
+
+1. Find all Ruby files in the specified directory
+2. Initialize a report object to store our results
+3. Process each file found:
+   - Read the file content
+   - Count the methods defined
+   - Update the report with the analysis result
+4. Generate a summary report
+5. Write the report to a file
+
+## Key Components
+
+- `each` construct: Processes every Ruby file found in the directory
+- `repeat` construct: Used to generate the final summary (demonstrates a simple case of the repeat construct)
+- Both block-level and prompt-based steps
+
+## Running the Workflow
+
+To run this workflow, use the following command:
+
+```bash
+shadowenv exec -- bundle exec roast examples/iteration/simple_workflow.yml
+```
+
+The final report will be saved to a markdown file as specified in the output of the `write_report` step.
+
+## Learning Objectives
+
+- Understand how to use the `each` construct to iterate over a collection
+- Understand how to use the `repeat` construct for conditional repetition
+- Learn how to build and update data structures across workflow steps
+- See how to pass data between steps in an iteration workflow

data/examples/iteration/simple_workflow.yml

@@ -0,0 +1,58 @@
+name: Ruby Method Counter
+tools:
+  - Roast::Tools::ReadFile
+  - Roast::Tools::Grep
+  - Roast::Tools::WriteFile
+  - Roast::Tools::CodingAgent
+
+steps:
+  # Find all Ruby files in the specified directory
+  - find_ruby_files:
+      $(find lib/roast/workflow -type f -name "*.rb")
+
+  # Initialize a report object to store our results
+  - initialize_report:
+      $(echo '{"files_analyzed": 0, "total_methods": 0, "results": []}')
+
+  # Process each file found
+  - each: "{{output['find_ruby_files'].split('\n')}}"
+    as: "current_file"
+    steps:
+      # Read the file content
+      - read_file:
+          prompt: examples/iteration/prompts/analyze_file
+          model: claude-3-haiku-20240307
+          vars:
+            file_path: "{{ current_file }}"
+
+      # Update the report with the analysis result
+      - update_report:
+          prompt: examples/iteration/prompts/update_report
+          model: claude-3-haiku-20240307
+          vars:
+            file_path: "{{ current_file }}"
+            method_count: "{{ output['read_file']['method_count'] }}"
+            current_report: "{{ output['initialize_report'] }}"
+
+  # Generate the summary report after processing all files
+  - report_count:
+      $(echo "{{ output.initialize_report.files_analyzed }}")
+
+  # Repeat to generate the final summary - demonstrates the repeat construct
+  - repeat:
+      steps:
+        - generate_summary:
+            prompt: examples/iteration/prompts/generate_summary
+            model: claude-3-haiku-20240307
+            vars:
+              report_data: "{{ output['initialize_report'] }}"
+      until: "{{true}}"
+      max_iterations: 1
+
+  # Write the report to a file
+  - write_report:
+      prompt: examples/iteration/prompts/write_report
+      model: claude-3-haiku-20240307
+      vars:
+        report_data: "{{ output['initialize_report'] }}"
+        summary: "{{ output['generate_summary']['summary'] }}"

data/examples/iteration/update_fix_count/prompt.md

@@ -0,0 +1,26 @@
+I'll update the count of fixes that have been successfully applied.
+
+Current fix count: 
+```
+{{output.update_fix_count || 0}}
+```
+
+Verification result from the previous step:
+```json
+{{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}}";
+
+if (verificationStatus === "success" || verificationStatus === "partial") {
+  currentCount += 1;
+}
+
+return { fixes_applied: currentCount };
+```
+
+This updated count will be used to determine whether we've met our target for the number of fixes to implement.

data/examples/iteration/verify_fix/prompt.md

@@ -0,0 +1,29 @@
+I'll verify that the fix implemented in the previous step correctly addresses the identified issue.
+
+Here are the details of the issue that was fixed:
+```json
+{{output.select_next_issue}}
+```
+
+And here is the implementation of the fix:
+```json
+{{output.implement_fix}}
+```
+
+Now I'll read the updated file to verify the changes:
+```ruby
+{{read_file(output.select_next_issue.file_path)}}
+```
+
+I'll evaluate the fix based on these criteria:
+1. Does it fully address the identified issue?
+2. Did it introduce any new issues or regressions?
+3. Does it maintain the original functionality?
+4. Does it follow Ruby best practices and style conventions?
+5. Is it minimal and focused (changing only what was necessary)?
+
+Based on this evaluation, I'll provide:
+1. A verification status (success, partial, failure)
+2. Detailed reasoning for the status
+3. Any recommendations for further improvements or adjustments
+4. An overall assessment of the code quality improvement 

data/examples/iteration/workflow.yml

@@ -0,0 +1,42 @@
+name: Code Quality Analyzer
+tools:
+  - Roast::Tools::ReadFile
+  - Roast::Tools::Grep
+  - Roast::Tools::WriteFile
+  - Roast::Tools::UpdateFiles
+  - Roast::Tools::CodingAgent
+  - Roast::Tools::Cmd
+
+steps:
+  # Get all Ruby files from the target directory
+  - get_files_to_analyze:
+      $(find {{resource.target}} -name "*.rb" -not -path "*/vendor/*" | grep -v "test")
+
+  # Analyze each file and generate improvement recommendations
+  - each: "{{output['get_files_to_analyze'].split('\n')}}"
+    as: "current_file"
+    steps:
+      - read_file:
+          $(cat {{current_file}})
+      - analyze_complexity
+      - generate_recommendations
+
+  # After analyzing all files, sort issues by priority
+  - prioritize_issues
+  
+  # Process the highest priority issues first, until we've addressed a sufficient number
+  # or reached our iteration limit
+  - initialize_fixes:
+      $(echo "0")
+  
+  - repeat:
+      steps:
+        - select_next_issue
+        - implement_fix
+        - verify_fix
+        - update_fix_count
+      until: "{{output['update_fix_count']['fixes_applied'] >= 5 || output['select_next_issue']['no_issues_left'] == true}}"
+      max_iterations: 10
+  
+  # Generate a summary report of all changes made
+  - generate_report

data/examples/openrouter_example/workflow.yml

@@ -1,7 +1,7 @@
 name: OpenRouter Example
 api_provider: openrouter
 api_token: $(echo $OPENROUTER_API_KEY)
-model: anthropic/claude-3-haiku-20240307
+model: google/gemini-2.0-flash-001
 
 tools:
   - Roast::Tools::ReadFile
@@ -9,4 +9,4 @@ tools:
 
 steps:
   - analyze_input
-  - generate_response
+  - generate_response

data/examples/workflow_generator/README.md

@@ -0,0 +1,27 @@
+# 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

@@ -0,0 +1,34 @@
+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

@@ -0,0 +1,32 @@
+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

@@ -0,0 +1,14 @@
+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>