@specverse/engines 5.1.0 → 5.2.0

package/assets/prompts/core/base-terminal-prompt.md

@@ -1,201 +0,0 @@
-# SpecVerse Terminal Quick-Start Guide
-
-**For**: LLM Terminal Users (ChatGPT, Claude, Cursor, etc.)
-**Purpose**: Use SpecVerse standard prompts for specification generation and implementation
-**Version**: 7.0.0
-
-This guide shows how to use the **standard SpecVerse prompts** for terminal/chat-based AI interactions.
-
-## Available Standard Prompts (v7)
-
-SpecVerse provides four standard prompts with enhanced capabilities:
-
-1. **`create`** - Generate SpecVerse specifications from natural language requirements
-2. **`analyse`** - Extract specifications from existing codebases (reverse engineering)
-3. **`materialise`** - Generate complete implementations from specifications
-4. **`realize`** - Generate deployment configurations (environment-adaptive)
-
-Located in: `prompts/core/standard/v7/`
-
-## Quick Start: Using the Create Prompt
-
-The **create** prompt is your starting point for new projects:
-
-### Step 1: View the Full Prompt
-
-```bash
-cat prompts/core/standard/v7/create.prompt.yaml
-```
-
-### Step 2: Terminal-Ready Version
-
-Copy this complete prompt into your LLM:
-
-```
-You are a SpecVerse v3.2.0 specification creator that generates complete, well-structured specifications from natural language requirements.
-
-IMPORTANT: First, read these reference files if available:
-- node_modules/@specverse/lang/schema/SPECVERSE-SCHEMA-AI.yaml (AI guidance and examples)
-- node_modules/@specverse/lang/schema/MINIMAL-SYNTAX-REFERENCE.specly (complete syntax example)
-
-Your task is to:
-1. Analyze natural language requirements
-2. Extract core business entities and their relationships
-3. Generate complete SpecVerse specifications with:
-   - Models with attributes and behaviors
-   - Controllers with CURED operations
-   - Services with business logic
-   - Views for user interfaces
-   - Events for system communication
-   - Deployments for infrastructure
-   - Manifests for implementation details
-
-Use SpecVerse v3.2.0 syntax:
-- Attributes: name: Type modifiers
-- Types: String, Integer, UUID, Email, DateTime, Boolean, Money, Text
-- Modifiers: required, optional, unique, auto, searchable, indexed, default=value
-- Relations: hasMany, belongsTo, references
-
-Generate a SpecVerse specification from these requirements:
-
-Requirements: [YOUR REQUIREMENTS HERE]
-Project Type: [web-app/api/full-stack]
-Scale: [personal/startup/business/enterprise]
-Primary Technology: [nextjs/nestjs/express/auto]
-
-Please generate:
-1. Complete component specification with all models and relationships
-2. Implementation manifest with technology choices
-3. Deployment specification for the target environment
-```
-
-## Workflow Example: From Idea to Implementation
-
-### 1. Create Specification
-```
-Requirements: I need a guesthouse booking system where I can manage multiple properties, each with rooms that guests can book. Need to see bookings on a timeline and prevent double-booking.
-Project Type: full-stack
-Scale: business
-Primary Technology: nextjs
-```
-
-### 2. Generate Implementation (Materialise)
-After getting your specification, use the materialise prompt:
-
-```
-Generate a complete implementation from this SpecVerse specification:
-
-[PASTE YOUR SPECIFICATION HERE]
-
-Target Framework: nextjs
-Implementation Style: modern
-Data Consistency Level: strict
-Error Handling Strategy: comprehensive
-
-Generate:
-1. Complete project structure
-2. Database schema with migrations
-3. API routes with validation
-4. React components with state management
-5. Setup scripts (like start.sh)
-6. Documentation
-```
-
-### 3. Generate Deployment (Realize)
-For deployment configurations:
-
-```
-Generate deployment configurations from this SpecVerse specification:
-
-[PASTE YOUR SPECIFICATION HERE]
-
-Target Environment: [development/production/enterprise]
-Cloud Provider: [vercel/aws/local]
-
-For development: Generate Docker Compose and start.sh script
-For production: Generate infrastructure as code and CI/CD pipelines
-```
-
-## Complete Workflow Commands
-
-1. **Create** a specification from requirements
-2. **Save** as `spec.specly`
-3. **Materialise** into working code
-4. **Realize** deployment configurations
-5. **Run** with generated start scripts
-
-## Key Improvements in v7
-
-### Create (v7)
-- Better validation and type safety
-- Support for complex relationships
-- Event-driven architecture patterns
-- Modern deployment targets (Vercel, Netlify)
-
-### Materialise (v7)
-- **Data consistency focus** - Handles snake_case/camelCase mapping
-- **Multi-layer validation** - Database, API, and frontend
-- **Automated setup** - Generates start.sh style scripts
-- **Error handling** - Comprehensive error patterns
-
-### Realize (v7)
-- **Environment-adaptive** - Only generates what's needed
-- **Progressive enhancement** - Dev → Test → Prod → Enterprise
-- **Local dev support** - Quick start scripts and Docker Compose
-- **Zero-downtime** - Blue-green and canary deployments
-
-## Environment-Specific Generation
-
-### Development
-- Simple Docker Compose
-- start.sh quick-start script
-- Hot reload configuration
-- Basic debugging setup
-
-### Production
-- High availability infrastructure
-- Monitoring and alerting
-- Security hardening
-- Backup and recovery
-
-### Enterprise
-- Multi-region deployment
-- Compliance frameworks
-- Advanced security
-- Disaster recovery
-
-## Tips for Better Results
-
-1. **Be specific** about your requirements
-2. **Include examples** of the data you'll work with
-3. **Specify scale** to get appropriate architecture
-4. **Mention constraints** like compliance or performance
-5. **Describe user workflows** for better UX generation
-
-## Troubleshooting Common Issues
-
-### Data Mapping Issues
-If you see snake_case/camelCase problems:
-- Request "strict" data consistency level in materialise
-- Ask for explicit data mapping functions
-
-### Missing Bookings/Data
-Check for:
-- Database column name mapping (room_id vs roomId)
-- Date format conversions (ISO vs YYYY-MM-DD)
-- API response transformations
-
-### Connection Issues
-For database connections:
-- Use environment variables in scripts
-- Generate start.sh with explicit POSTGRES_URL
-- Include .env.example templates
-
-## Next Steps
-
-1. Start with the **create** prompt for your requirements
-2. Use **materialise** to generate implementation
-3. Apply **realize** for deployment setup
-4. Iterate based on your specific needs
-
-Remember: v7 prompts are environment-aware and will adapt their output to your actual needs!

package/assets/prompts/core/examples/example-usage.ts

@@ -1,140 +0,0 @@
-/**
- * Example usage of the SpecVerse Prompt System
- * Demonstrates how to load and process prompts with the PromptLoader
- */
-
-import { promptLoader } from '../src/prompts/prompt-loader';
-
-async function demonstratePromptUsage() {
-  console.log('SpecVerse Prompt System Demo\n');
-
-  try {
-    // 1. List all available prompts
-    console.log('📋 Available prompts:');
-    const prompts = await promptLoader.listPrompts();
-    prompts.forEach(({ path, definition }) => {
-      console.log(`  - ${path}: ${definition.description}`);
-    });
-    console.log('');
-
-    // 2. Load and process the 'create' prompt
-    console.log('🔧 Processing "create" prompt...');
-    const createPrompt = await promptLoader.processPrompt(
-      'standard/create',
-      {
-        requirements: 'Build a simple blog where users can write posts with titles and content. Posts should have tags for organization.',
-        scale: 'personal',
-        preferredTech: 'nextjs'
-      }
-    );
-
-    console.log('System Prompt Preview:');
-    console.log(createPrompt.system.substring(0, 200) + '...\n');
-
-    console.log('User Prompt Preview:');
-    console.log(createPrompt.user.substring(0, 300) + '...\n');
-
-    // 3. Load and process the 'analyse' prompt
-    console.log('🔍 Processing "analyse" prompt...');
-    const analysePrompt = await promptLoader.processPrompt(
-      'standard/analyse',
-      {
-        applicationPath: '/path/to/my-app',
-        frameworkType: 'nextjs',
-        directoryStructure: 'my-app/\n├── app/\n│   └── api/\n└── package.json',
-        filesContent: '=== package.json ===\n{ "name": "my-app" }'
-      }
-    );
-
-    console.log('Analysis Prompt Ready:');
-    console.log(`- System prompt length: ${analysePrompt.system.length} chars`);
-    console.log(`- User prompt length: ${analysePrompt.user.length} chars`);
-    console.log(`- Context includes: ${Object.keys(analysePrompt.context.includes).join(', ')}\n`);
-
-    // 4. Validate a prompt
-    console.log('✅ Validating prompt structure...');
-    const prompt = await promptLoader.loadPrompt('standard/create');
-    const validation = promptLoader.validatePrompt(prompt);
-    
-    console.log(`Validation result: ${validation.valid ? 'PASSED' : 'FAILED'}`);
-    if (!validation.valid) {
-      console.log('Errors:', validation.errors);
-    }
-
-  } catch (error) {
-    console.error('Error:', error.message);
-  }
-}
-
-async function exampleLLMIntegration() {
-  console.log('\n🤖 Example LLM Integration\n');
-
-  try {
-    // Simulate loading a prompt and sending to LLM
-    const prompt = await promptLoader.processPrompt(
-      'standard/create',
-      {
-        requirements: 'Create an e-commerce site with products and shopping cart',
-        scale: 'business'
-      }
-    );
-
-    // This is what you would send to an LLM provider
-    const llmRequest = {
-      messages: [
-        { role: 'system', content: prompt.system },
-        { role: 'user', content: prompt.user }
-      ],
-      max_tokens: prompt.context.max_tokens,
-      temperature: prompt.context.temperature,
-      top_p: prompt.context.top_p
-    };
-
-    console.log('LLM Request Structure:');
-    console.log(`- Messages: ${llmRequest.messages.length}`);
-    console.log(`- Max tokens: ${llmRequest.max_tokens}`);
-    console.log(`- Temperature: ${llmRequest.temperature}`);
-    console.log(`- Top P: ${llmRequest.top_p}`);
-
-    // Mock LLM response
-    const mockResponse = `
-components:
-  EcommercePlatform:
-    version: "1.0.0"
-    description: "E-commerce platform"
-    
-    models:
-      Product:
-        attributes:
-          name: String required searchable
-          price: Money required
-          inventory: Integer required default=0 min=0
-        relationships:
-          category: belongsTo Category required
-          
-      Category:
-        attributes:
-          name: String required unique
-        relationships:
-          products: hasMany Product
-    `;
-
-    console.log('\nMock LLM Response:');
-    console.log(mockResponse);
-
-  } catch (error) {
-    console.error('Error:', error.message);
-  }
-}
-
-async function runExamples() {
-  await demonstratePromptUsage();
-  await exampleLLMIntegration();
-}
-
-// Run examples if this file is executed directly
-if (require.main === module) {
-  runExamples().catch(console.error);
-}
-
-export { demonstratePromptUsage, exampleLLMIntegration };

package/assets/prompts/core/schemas/prompt.schema.json

@@ -1,309 +0,0 @@
-{
-  "$id": "https://specverse.org/schemas/prompt-v1.0.0.yaml",
-  "title": "SpecVerse Prompt Schema",
-  "description": "Schema for validating SpecVerse AI prompt definitions",
-  "type": "object",
-  "required": [
-    "name",
-    "version",
-    "description",
-    "system",
-    "user",
-    "context",
-    "validation"
-  ],
-  "properties": {
-    "name": {
-      "type": "string",
-      "pattern": "^[a-z][a-z0-9-]*$",
-      "description": "Unique prompt identifier (kebab-case)"
-    },
-    "version": {
-      "type": "string",
-      "pattern": "^\\d+\\.\\d+\\.\\d+$",
-      "description": "Semantic version (e.g., 1.0.0)"
-    },
-    "description": {
-      "type": "string",
-      "maxLength": 200,
-      "description": "Brief description of prompt purpose"
-    },
-    "author": {
-      "type": "string",
-      "description": "Prompt author or team"
-    },
-    "tags": {
-      "type": "array",
-      "items": {
-        "type": "string"
-      },
-      "description": "Categorization tags"
-    },
-    "system": {
-      "type": "object",
-      "required": [
-        "role",
-        "context"
-      ],
-      "properties": {
-        "role": {
-          "type": "string",
-          "description": "System role description for the LLM"
-        },
-        "context": {
-          "type": "string",
-          "description": "Required context and background"
-        },
-        "capabilities": {
-          "type": "array",
-          "items": {
-            "type": "string"
-          },
-          "description": "List of capabilities the system should demonstrate"
-        },
-        "constraints": {
-          "type": "array",
-          "items": {
-            "type": "string"
-          },
-          "description": "Limitations or rules to follow"
-        }
-      }
-    },
-    "user": {
-      "type": "object",
-      "required": [
-        "template"
-      ],
-      "properties": {
-        "template": {
-          "type": "string",
-          "description": "User prompt template with {{variables}}"
-        },
-        "variables": {
-          "type": "array",
-          "items": {
-            "type": "object",
-            "required": [
-              "name",
-              "type"
-            ],
-            "properties": {
-              "name": {
-                "type": "string",
-                "pattern": "^[a-z][a-zA-Z0-9]*$"
-              },
-              "type": {
-                "type": "string",
-                "enum": [
-                  "string",
-                  "number",
-                  "boolean",
-                  "object",
-                  "array"
-                ]
-              },
-              "required": {
-                "type": "boolean",
-                "default": false
-              },
-              "description": {
-                "type": "string"
-              },
-              "default": {
-                "description": "Default value if not provided"
-              },
-              "validation": {
-                "type": "string",
-                "description": "Validation rule or regex pattern"
-              }
-            }
-          }
-        }
-      }
-    },
-    "context": {
-      "type": "object",
-      "required": [
-        "includes"
-      ],
-      "properties": {
-        "includes": {
-          "type": "array",
-          "items": {
-            "type": "object",
-            "properties": {
-              "schema": {
-                "type": "string",
-                "description": "Schema file to include"
-              },
-              "library": {
-                "type": "string",
-                "description": "Library to include"
-              },
-              "template": {
-                "type": "string",
-                "description": "Template to include"
-              }
-            }
-          },
-          "description": "Context files to include"
-        },
-        "max_tokens": {
-          "type": "integer",
-          "minimum": 100,
-          "maximum": 32000,
-          "default": 4000,
-          "description": "Maximum tokens for response"
-        },
-        "temperature": {
-          "type": "number",
-          "minimum": 0,
-          "maximum": 2,
-          "default": 0.7,
-          "description": "LLM temperature setting"
-        },
-        "top_p": {
-          "type": "number",
-          "minimum": 0,
-          "maximum": 1,
-          "default": 1,
-          "description": "LLM top_p setting"
-        }
-      }
-    },
-    "validation": {
-      "type": "object",
-      "properties": {
-        "input": {
-          "type": "array",
-          "items": {
-            "type": "object",
-            "properties": {
-              "rule": {
-                "type": "string",
-                "description": "Input validation rule"
-              },
-              "required": {
-                "type": "boolean",
-                "default": true
-              }
-            }
-          },
-          "description": "Input validation rules"
-        },
-        "output": {
-          "type": "array",
-          "items": {
-            "type": "object",
-            "properties": {
-              "rule": {
-                "type": "string",
-                "description": "Output validation rule"
-              },
-              "format": {
-                "type": "string",
-                "enum": [
-                  "yaml",
-                  "json",
-                  "markdown",
-                  "text"
-                ]
-              },
-              "schema": {
-                "type": "string",
-                "description": "Schema to validate against"
-              }
-            }
-          },
-          "description": "Output validation rules"
-        }
-      }
-    },
-    "examples": {
-      "type": "array",
-      "items": {
-        "type": "object",
-        "required": [
-          "input",
-          "output"
-        ],
-        "properties": {
-          "name": {
-            "type": "string",
-            "description": "Example name"
-          },
-          "description": {
-            "type": "string",
-            "description": "What this example demonstrates"
-          },
-          "input": {
-            "description": "Example input"
-          },
-          "output": {
-            "description": "Expected output"
-          },
-          "explanation": {
-            "type": "string",
-            "description": "Explanation of the example"
-          }
-        }
-      },
-      "description": "Example usage cases"
-    },
-    "metadata": {
-      "type": "object",
-      "properties": {
-        "created": {
-          "type": "string",
-          "format": "date-time"
-        },
-        "updated": {
-          "type": "string",
-          "format": "date-time"
-        },
-        "tested_with": {
-          "type": "array",
-          "items": {
-            "type": "object",
-            "properties": {
-              "provider": {
-                "type": "string",
-                "enum": [
-                  "openai",
-                  "anthropic",
-                  "azure",
-                  "local"
-                ]
-              },
-              "model": {
-                "type": "string"
-              },
-              "success_rate": {
-                "type": "number",
-                "minimum": 0,
-                "maximum": 100
-              }
-            }
-          },
-          "description": "Testing results with different providers"
-        },
-        "performance": {
-          "type": "object",
-          "properties": {
-            "avg_response_time": {
-              "type": "number",
-              "description": "Average response time in seconds"
-            },
-            "avg_tokens_used": {
-              "type": "integer",
-              "description": "Average tokens consumed"
-            }
-          }
-        }
-      },
-      "description": "Prompt metadata and performance metrics"
-    }
-  },
-  "additionalProperties": false
-}