feat: Implement Issue #54 - Add content field instruction capabilities

This implementation adds comprehensive support for content field instructions
that provide guidance for document generation from schemas.

## Key Features Added:

### CLI Options
- `--include-content-instructions` flag to enable content instruction fields
- `--instruction-type` parameter with options: description, example, constraint, template
- Full integration with existing outline mode and heading text capture features

### Schema Generation Enhancements
- Content instruction fields (x-markitect-content-instructions) with contextual guidance text
- Instruction type metadata (x-markitect-instruction-type) for type specification
- Metaschema extension (x-markitect-content-instructions-enabled) for feature detection
- Support for headings, paragraphs, and lists content instructions

### Error Handling
- InvalidInstructionTypeError for robust validation of instruction type parameters
- Comprehensive input validation with clear error messages

### Integration and Compatibility
- Seamless integration with outline mode and heading text capture
- Full backward compatibility - existing behavior unchanged when feature disabled
- Works with all existing CLI options and modes

### Documentation
- Updated CLI help with examples and detailed feature descriptions
- Clear documentation of all instruction types and their purposes

## Technical Implementation:
- Enhanced SchemaGenerator with content instruction generation logic
- Added `_generate_content_instruction` method for contextual instruction text
- Extended schema structure to include instruction metadata
- Maintained clean separation of concerns and existing code patterns

## Testing and Validation:
- Comprehensive test coverage following TDD8 methodology
- All existing functionality preserved and tested
- Integration tests for all feature combinations
- Error handling and edge case validation

This completes Issue #54 with full feature implementation, documentation,
and comprehensive testing coverage.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

markitect/cli.py

@@ -1455,8 +1455,10 @@ def ast_stats(config, file_path, format):
 @click.option('--mode', type=click.Choice(['outline']), help='Generation mode: outline for structure-focused schemas')
 @click.option('--depth', type=int, help='Maximum depth for outline mode (similar to --max-depth)')
 @click.option('--capture-heading-text', is_flag=True, help='Capture exact heading text as schema constraints')
+@click.option('--include-content-instructions', is_flag=True, help='Include content field instructions for document generation')
+@click.option('--instruction-type', type=click.Choice(['description', 'example', 'constraint', 'template']), default='description', help='Type of content instructions to generate')
 @pass_config
-def generate_schema(config, file_path, max_depth, output, outfile, output_format, mode, depth, capture_heading_text):
+def generate_schema(config, file_path, max_depth, output, outfile, output_format, mode, depth, capture_heading_text, include_content_instructions, instruction_type):
     """
     Generate a JSON schema from a markdown file's AST structure.
 
@@ -1475,6 +1477,11 @@ def generate_schema(config, file_path, max_depth, output, outfile, output_format
         markitect schema-generate --capture-heading-text document.md
         markitect schema-generate --mode outline --capture-heading-text --depth 2 document.md
 
+        # Content instructions for document generation guidance
+        markitect schema-generate --include-content-instructions document.md
+        markitect schema-generate --include-content-instructions --instruction-type example document.md
+        markitect schema-generate --mode outline --include-content-instructions --instruction-type template document.md
+
     Modes:
         Default: Standard schema generation with structural analysis
         Outline: Structure-focused schema with heading text capture and metaschema extensions
@@ -1482,6 +1489,14 @@ def generate_schema(config, file_path, max_depth, output, outfile, output_format
     Heading Text Capture:
         When --capture-heading-text is enabled, the schema will include exact heading text
         as enum constraints, enabling validation to enforce specific heading text requirements.
+
+    Content Instructions:
+        When --include-content-instructions is enabled, the schema will include guidance fields
+        for document generation. Use --instruction-type to specify the type of instructions:
+        - description: Descriptive guidance for content authors
+        - example: Example-based content guidance
+        - constraint: Content constraint specifications
+        - template: Template-based content structure
     """
     try:
         # Handle parameter conflicts and defaults
@@ -1517,7 +1532,9 @@ def generate_schema(config, file_path, max_depth, output, outfile, output_format
             max_depth=final_depth,
             mode=mode,
             outline_depth=depth if mode == 'outline' else None,
-            capture_heading_text=capture_heading_text
+            capture_heading_text=capture_heading_text,
+            include_content_instructions=include_content_instructions,
+            instruction_type=instruction_type
         )
 
         # Format output

markitect/exceptions.py

@@ -168,4 +168,15 @@ class InvalidSchemaError(MarkitectError):
     - Schema doesn't conform to JSON Schema specification
     - Schema file cannot be loaded or parsed
     """
+    pass
+
+
+class InvalidInstructionTypeError(MarkitectError):
+    """Errors related to invalid content instruction types.
+
+    Raised when:
+    - Instruction type is not one of the supported types
+    - Instruction type parameter is malformed
+    - Instruction type conflicts with other options
+    """
     pass

markitect/schema_generator.py

@@ -12,7 +12,7 @@ from pathlib import Path
 from typing import Dict, List, Any, Optional, Set
 
 from .parser import parse_markdown_to_ast
-from .exceptions import FileNotFoundError, InvalidDepthError
+from .exceptions import FileNotFoundError, InvalidDepthError, InvalidInstructionTypeError
 
 
 class SchemaGenerator:
@@ -34,7 +34,9 @@ class SchemaGenerator:
         max_depth: Optional[int] = None,
         mode: Optional[str] = None,
         outline_depth: Optional[int] = None,
-        capture_heading_text: bool = False
+        capture_heading_text: bool = False,
+        include_content_instructions: bool = False,
+        instruction_type: str = 'description'
     ) -> Dict[str, Any]:
         """
         Generate a JSON schema from a markdown file's AST structure.
@@ -45,6 +47,8 @@ class SchemaGenerator:
             mode: Generation mode ('outline' for structure-focused schemas)
             outline_depth: Depth limit for outline mode
             capture_heading_text: Whether to capture exact heading text as constraints
+            include_content_instructions: Whether to include content instruction fields
+            instruction_type: Type of content instructions ('description', 'example', 'constraint', 'template')
 
         Returns:
             JSON schema as a dictionary
@@ -60,6 +64,11 @@ class SchemaGenerator:
         if max_depth is not None and max_depth < 1:
             raise InvalidDepthError(f"max_depth must be >= 1, got: {max_depth}")
 
+        # Validate instruction type
+        valid_instruction_types = {'description', 'example', 'constraint', 'template'}
+        if instruction_type not in valid_instruction_types:
+            raise InvalidInstructionTypeError(f"Invalid instruction type '{instruction_type}'. Must be one of: {', '.join(valid_instruction_types)}")
+
         # Read and parse the markdown file
         content = file_path.read_text(encoding='utf-8')
         ast_tokens = parse_markdown_to_ast(content)
@@ -68,7 +77,15 @@ class SchemaGenerator:
         structure_analysis = self._analyze_ast_structure(ast_tokens, max_depth)
 
         # Generate the JSON schema
-        schema = self._create_json_schema(structure_analysis, file_path.name, mode=mode, outline_depth=outline_depth, capture_heading_text=capture_heading_text)
+        schema = self._create_json_schema(
+            structure_analysis,
+            file_path.name,
+            mode=mode,
+            outline_depth=outline_depth,
+            capture_heading_text=capture_heading_text,
+            include_content_instructions=include_content_instructions,
+            instruction_type=instruction_type
+        )
 
         return schema
 
@@ -186,7 +203,9 @@ class SchemaGenerator:
         filename: str,
         mode: Optional[str] = None,
         outline_depth: Optional[int] = None,
-        capture_heading_text: bool = False
+        capture_heading_text: bool = False,
+        include_content_instructions: bool = False,
+        instruction_type: str = 'description'
     ) -> Dict[str, Any]:
         """
         Create a JSON schema from structural analysis.
@@ -197,6 +216,8 @@ class SchemaGenerator:
             mode: Generation mode ('outline' for structure-focused schemas)
             outline_depth: Depth limit for outline mode
             capture_heading_text: Whether to capture exact heading text as constraints
+            include_content_instructions: Whether to include content instruction fields
+            instruction_type: Type of content instructions to generate
 
         Returns:
             JSON schema dictionary
@@ -222,6 +243,10 @@ class SchemaGenerator:
         if capture_heading_text:
             schema["x-markitect-heading-text-capture"] = True
 
+        # Add metaschema extension for content instructions
+        if include_content_instructions:
+            schema["x-markitect-content-instructions-enabled"] = True
+
         # Add heading structure
         if analysis['headings']:
             heading_properties = {}
@@ -235,16 +260,36 @@ class SchemaGenerator:
                     else:
                         content_property = {"type": "string"}
 
+                    # Build properties for the heading item
+                    item_properties = {
+                        "content": content_property,
+                        "level": {"type": "integer"},
+                        "position": {"type": "integer"}
+                    }
+
+                    # Add content instruction fields if enabled
+                    if include_content_instructions:
+                        # Generate appropriate instruction text based on heading level
+                        level_num = int(level_key.split('_')[1])
+                        section_name = f"level {level_num} heading"
+                        instruction_text = self._generate_content_instruction(section_name, instruction_type)
+
+                        item_properties["x-markitect-content-instructions"] = {
+                            "type": "string",
+                            "const": instruction_text
+                        }
+
+                        item_properties["x-markitect-instruction-type"] = {
+                            "type": "string",
+                            "enum": [instruction_type]
+                        }
+
                     heading_properties[level_key] = {
                         "type": "array",
                         "description": f"Headings at {level_key.replace('_', ' ')}",
                         "items": {
                             "type": "object",
-                            "properties": {
+                            "properties": item_properties,
-                                "content": content_property,
-                                "level": {"type": "integer"},
-                                "position": {"type": "integer"}
-                            },
                             "required": ["content", "level"]
                         },
                         "minItems": len(headings),
@@ -272,13 +317,33 @@ class SchemaGenerator:
 
         for element_name, (description, element_list) in structural_elements.items():
             if element_list:
-                schema["properties"][element_name] = {
+                # Build base schema for the element
+                element_schema = {
                     "type": "array",
                     "description": description,
                     "minItems": len(element_list),
                     "maxItems": len(element_list)
                 }
 
+                # Add content instructions for paragraphs and lists if enabled
+                if include_content_instructions and element_name in ["paragraphs", "lists"]:
+                    element_schema["items"] = {
+                        "type": "object",
+                        "properties": {
+                            "content": {"type": "string"},
+                            "x-markitect-content-instructions": {
+                                "type": "string",
+                                "const": self._generate_content_instruction(element_name, instruction_type)
+                            },
+                            "x-markitect-instruction-type": {
+                                "type": "string",
+                                "enum": [instruction_type]
+                            }
+                        }
+                    }
+
+                schema["properties"][element_name] = element_schema
+
         # Add metadata
         schema["properties"]["metadata"] = {
             "type": "object",
@@ -375,4 +440,27 @@ class SchemaGenerator:
                 elif child_type in ['em_open', 'strong_open']:
                     result['emphasis'].append({"type": child_type})
 
-        return result
+        return result
+
+    def _generate_content_instruction(self, heading_text: str, instruction_type: str) -> str:
+        """
+        Generate appropriate content instruction text based on heading and instruction type.
+
+        Args:
+            heading_text: The text of the heading
+            instruction_type: Type of instruction to generate
+
+        Returns:
+            Instruction text for the content field
+        """
+        if instruction_type == "description":
+            return f"Provide content for the '{heading_text}' section"
+        elif instruction_type == "example":
+            return f"Example content for the '{heading_text}' section"
+        elif instruction_type == "constraint":
+            return f"Content must be relevant to '{heading_text}'"
+        elif instruction_type == "template":
+            return f"Template content for '{heading_text}' section"
+        else:
+            # Default fallback
+            return f"Content for the '{heading_text}' section"