get_template_guidance

Get detailed guidance for filling out a template-based input.

COMPLETE TEMPLATE HANDLING PROCESS:

STEP 1 - TEMPLATE IDENTIFICATION:

• Called for inputs that have a templateFile property

• Provides decoded template content and structure explanation

• Returns required fields, format-specific tips, and validation rules

PREFILLING PROCESS:

1. Analyze template structure for external dependencies

2. Prefill template with realistic values based on the instructions

RELEVANCE FILTERING:

• ANALYZE task description and user use case to create targeted search queries

• EXTRACT key terms from rule purpose and task capabilities

• COMBINE system name with specific functionality being configured

• PRIORITIZE documentation that matches the exact use case scenario

STEP 3 - ENHANCED TEMPLATE PRESENTATION TO USER: Show the template with this EXACT format: "Now configuring: [X of Y inputs]

Task: {task_name} Input: {input_name} - {description}

You can:

• Accept these prefilled values (type 'accept')

• Modify specific sections (provide your modifications)

• Replace entirely (provide your complete configuration)

Please review and confirm or modify the prefilled configuration:"

STEP 4 - FALLBACK TO ORIGINAL TEMPLATE: If no documentation found or prefilling fails:

• Show original empty template with standard format

• Include note: "No documentation found for prefilling. Please provide your configuration."

• Continue with existing workflow

STEP 5 - COLLECT USER CONTENT:

• Wait for the user to provide their response (accept/modify/replace)

• Handle "accept" by using prefilled content

• Handle modifications by merging with prefilled baseline

• Handle complete replacement with user content

• Do NOT proceed until the user provides content

• NEVER use template content as default values without documentation analysis

STEP 6 - PROCESS TEMPLATE INPUT:

• Call collect_template_input(task_name, input_name, user_content)

• Include documentation source metadata

• Validates content format, checks required fields, uploads file

• Returns file URL for use in rule structure

TEMPLATE FORMAT HANDLING:

• JSON: Must be valid JSON with proper brackets and quotes

• TOML: Must follow TOML syntax with proper sections [section_name]

• YAML: Must have correct indentation and structure

• XML: Must be well-formed XML with proper tags

VALIDATION RULES:

• Format-specific syntax validation

• Required field presence checking

• Data type validation where applicable

• Template structure compliance

• Documentation standard compliance (when applicable)

CRITICAL TEMPLATE RULES:

• ALWAYS call get_template_guidance() for inputs with templates

• ALWAYS analyze documentation before showing template to user

• ALWAYS show the prefilled template (or original if no docs found) with exact presentation format

• ALWAYS wait for the user to provide response (accept/modify/replace)

• ALWAYS call collect_template_input() to process user content

• NEVER use template content directly - always use documentation-enhanced or user-provided content

• ALWAYS use returned file URLs in rule structure

PROGRESS TRACKING:

• Show "Now configuring: [X of Y inputs]" for user progress

• Include clear task and input identification

• Provide format-specific guidance and tips

• Include documentation analysis results and source citations

Args: task_name: Name of the task input_name: Name of the input that has a template

Returns: Dict containing template content, documentation analysis, prefilled values, and guidance