@hazeljs/cli 0.7.9 → 0.8.1

package/@template-ai-native/README.md

@@ -3,7 +3,7 @@
 A complete AI-native backend application with HazelJS, featuring:
 
 - 🤖 **AI Chat Service** - OpenAI-powered chat endpoints
-- 🧠 **AI Agents** - Agents with tools and capabilities  
+- 🧠 **AI Agents** - Agents with tools and capabilities
 - 📚 **RAG System** - Document ingestion and semantic search
 - 🏥 **Health Checks** - Application monitoring
 - 📊 **Inspector** - Development tools and debugging
@@ -13,29 +13,33 @@ A complete AI-native backend application with HazelJS, featuring:
 ## Quick Start
 
 1. **Install dependencies**
+
    ```bash
    npm install
    ```
 
 2. **Configure environment**
+
    ```bash
    cp .env.example .env
    # Add your OpenAI API key to .env
    ```
 
 3. **Start development server**
+
    ```bash
    npm run dev
    ```
 
 4. **Visit the application**
    - App: http://localhost:3000
-   - Inspector: http://localhost:3000/__hazel
+   - Inspector: http://localhost:3000/\_\_hazel
    - Health: http://localhost:3000/health
 
 ## Available Endpoints
 
 ### AI Chat
+
 ```bash
 curl -X POST http://localhost:3000/chat \
   -H "Content-Type: application/json" \
@@ -43,6 +47,7 @@ curl -X POST http://localhost:3000/chat \
 ```
 
 ### AI Agent (with tools)
+
 ```bash
 curl -X POST http://localhost:3000/agent \
   -H "Content-Type: application/json" \
@@ -50,6 +55,7 @@ curl -X POST http://localhost:3000/agent \
 ```
 
 ### RAG Document Ingestion
+
 ```bash
 curl -X POST http://localhost:3000/rag/ingest \
   -H "Content-Type: application/json" \
@@ -57,6 +63,7 @@ curl -X POST http://localhost:3000/rag/ingest \
 ```
 
 ### RAG Search
+
 ```bash
 curl -X POST http://localhost:3000/rag/search \
   -H "Content-Type: application/json" \
@@ -68,17 +75,20 @@ curl -X POST http://localhost:3000/rag/search \
 ### Using Docker Compose (Recommended)
 
 1. **Configure environment**
+
    ```bash
    cp .env.example .env
    # Add your OpenAI API key
    ```
 
 2. **Start all services**
+
    ```bash
    docker-compose up -d
    ```
 
 3. **View logs**
+
    ```bash
    docker-compose logs -f hazeljs-ai-app
    ```
@@ -91,6 +101,7 @@ curl -X POST http://localhost:3000/rag/search \
 ### Using Docker (Standalone)
 
 1. **Build the image**
+
    ```bash
    docker build -t hazeljs-ai-app .
    ```
@@ -105,12 +116,13 @@ curl -X POST http://localhost:3000/rag/search \
 The `docker-compose.yml` includes:
 
 - **hazeljs-ai-app** - Main application (port 3000)
-- **redis** - Caching and queues (port 6379) 
+- **redis** - Caching and queues (port 6379)
 - **postgres** - Database with pgvector extension (port 5432)
 
 ## API Testing with Postman
 
 1. **Import the collection**
+
    ```bash
    # Import HazelJS-AI-Native.postman_collection.json into Postman
    ```
@@ -178,7 +190,7 @@ npm run db:seed
 The template uses the `pgvector/pgvector` Docker image which includes the vector extension. Prisma automatically handles the vector indexes when you run `db:push`. The schema includes:
 
 - **Vector embeddings** stored as `Float[]` for RAG search
-- **Full-text search index** on the `content` field  
+- **Full-text search index** on the `content` field
 - **JSONB index** on the `metadata` field
 
 No manual SQL required - Prisma handles everything!
@@ -201,7 +213,7 @@ npm run db:generate
 The template includes:
 
 - **Documents** - RAG document storage with vector embeddings
-- **AgentConversations** - AI agent interaction history  
+- **AgentConversations** - AI agent interaction history
 - **ChatHistory** - AI chat session logs
 
 ### Using Docker with Database
@@ -254,6 +266,7 @@ npm run format
 ### Environment Setup
 
 1. **Set production variables**
+
    ```bash
    export NODE_ENV=production
    export OPENAI_API_KEY=your_production_key
@@ -261,6 +274,7 @@ npm run format
    ```
 
 2. **Deploy with Docker**
+
    ```bash
    docker-compose -f docker-compose.yml up -d
    ```

package/@template-ai-native/package.json

@@ -1,6 +1,6 @@
 {
   "name": "hazeljs-ai-native-app",
-  "version": "0.7.9",
+  "version": "0.8.1",
   "description": "A HazelJS AI-native application with agents, RAG, and chat",
   "main": "dist/index.js",
   "scripts": {

package/@template-ai-native/prisma/seed.ts

@@ -15,7 +15,8 @@ async function main() {
   // Sample documents for RAG demonstration
   const sampleDocuments = [
     {
-      content: 'HazelJS is a TypeScript framework for building AI-native backend applications. It provides built-in support for AI agents, RAG (Retrieval-Augmented Generation), and seamless integration with LLM providers like OpenAI, Anthropic, and Ollama.',
+      content:
+        'HazelJS is a TypeScript framework for building AI-native backend applications. It provides built-in support for AI agents, RAG (Retrieval-Augmented Generation), and seamless integration with LLM providers like OpenAI, Anthropic, and Ollama.',
       metadata: {
         source: 'documentation',
         type: 'introduction',
@@ -24,7 +25,8 @@ async function main() {
       },
     },
     {
-      content: 'TypeScript decorators provide a way to add metadata and modify the behavior of classes, methods, and properties. In HazelJS, decorators like @Controller, @Get, @Post, @Service, and @Agent are used to define the application structure and routing.',
+      content:
+        'TypeScript decorators provide a way to add metadata and modify the behavior of classes, methods, and properties. In HazelJS, decorators like @Controller, @Get, @Post, @Service, and @Agent are used to define the application structure and routing.',
       metadata: {
         source: 'typescript-guide',
         type: 'tutorial',
@@ -33,7 +35,8 @@ async function main() {
       },
     },
     {
-      content: 'AI agents in HazelJS can use tools to perform actions like API calls, database queries, or external service integrations. The @Agent decorator defines an agent, and @Tool decorator defines its capabilities.',
+      content:
+        'AI agents in HazelJS can use tools to perform actions like API calls, database queries, or external service integrations. The @Agent decorator defines an agent, and @Tool decorator defines its capabilities.',
       metadata: {
         source: 'agent-guide',
         type: 'tutorial',
@@ -42,7 +45,8 @@ async function main() {
       },
     },
     {
-      content: 'RAG (Retrieval-Augmented Generation) combines document retrieval with LLM generation to provide more accurate and context-aware responses. HazelJS provides built-in RAG services with vector similarity search.',
+      content:
+        'RAG (Retrieval-Augmented Generation) combines document retrieval with LLM generation to provide more accurate and context-aware responses. HazelJS provides built-in RAG services with vector similarity search.',
       metadata: {
         source: 'rag-guide',
         type: 'tutorial',
@@ -51,7 +55,8 @@ async function main() {
       },
     },
     {
-      content: 'The HazelJS Inspector is a development dashboard available at /__hazel that provides real-time insights into your application, including module dependencies, request metrics, and AI agent performance.',
+      content:
+        'The HazelJS Inspector is a development dashboard available at /__hazel that provides real-time insights into your application, including module dependencies, request metrics, and AI agent performance.',
       metadata: {
         source: 'development-guide',
         type: 'tutorial',
@@ -66,7 +71,7 @@ async function main() {
     try {
       // Generate embedding for the document
       const embedding = await embeddings.embed(doc.content);
-      
+
       // Use raw SQL to insert document with vector embedding
       await prisma.$executeRaw`
         INSERT INTO documents (id, content, metadata, embedding, "createdAt", "updatedAt")
@@ -79,7 +84,7 @@ async function main() {
           NOW()
         )
       `;
-      
+
       console.log(`✅ Created document: ${doc.metadata.source}`);
     } catch (error) {
       console.error(`❌ Failed to create document: ${doc.metadata.source}`, error);
@@ -128,14 +133,16 @@ async function main() {
     {
       sessionId: 'chat-session-1',
       userMessage: 'What is HazelJS?',
-      aiResponse: 'HazelJS is a TypeScript framework for building AI-native backend applications with built-in support for AI agents, RAG, and LLM integration.',
+      aiResponse:
+        'HazelJS is a TypeScript framework for building AI-native backend applications with built-in support for AI agents, RAG, and LLM integration.',
       model: 'gpt-4',
       tokensUsed: 156,
     },
     {
       sessionId: 'chat-session-1',
       userMessage: 'How do I create an AI agent?',
-      aiResponse: 'You can create an AI agent in HazelJS using the @Agent decorator and defining tools with @Tool decorator. Here\'s an example: @Agent({name: "MyAgent"}) class MyAgent { @Tool({description: "My tool"}) async myTool() { return "result"; } }',
+      aiResponse:
+        'You can create an AI agent in HazelJS using the @Agent decorator and defining tools with @Tool decorator. Here\'s an example: @Agent({name: "MyAgent"}) class MyAgent { @Tool({description: "My tool"}) async myTool() { return "result"; } }',
       model: 'gpt-4',
       tokensUsed: 234,
     },

package/@template-ai-native/src/agent/agent.controller.ts

@@ -91,16 +91,26 @@ export class WeatherAgent {
     let celsius: number;
 
     switch (fromUnit.toLowerCase()) {
-      case 'fahrenheit': celsius = (value - 32) * (5 / 9); break;
-      case 'kelvin':     celsius = value - 273.15; break;
-      default:           celsius = value;
+      case 'fahrenheit':
+        celsius = (value - 32) * (5 / 9);
+        break;
+      case 'kelvin':
+        celsius = value - 273.15;
+        break;
+      default:
+        celsius = value;
     }
 
     let result: number;
     switch (toUnit.toLowerCase()) {
-      case 'fahrenheit': result = celsius * (9 / 5) + 32; break;
-      case 'kelvin':     result = celsius + 273.15; break;
-      default:           result = celsius;
+      case 'fahrenheit':
+        result = celsius * (9 / 5) + 32;
+        break;
+      case 'kelvin':
+        result = celsius + 273.15;
+        break;
+      default:
+        result = celsius;
     }
 
     return {
@@ -134,7 +144,7 @@ export class WeatherAgent {
 export class AgentController {
   constructor(
     private readonly agent: WeatherAgent,
-    private readonly agentService: AgentService,
+    private readonly agentService: AgentService
   ) {}
 
   @Post()
@@ -160,7 +170,9 @@ export class AgentController {
       if (chunk.type === 'token') {
         res.write(`data: ${JSON.stringify({ type: 'token', content: chunk.content })}\n\n`);
       } else if (chunk.type === 'step') {
-        res.write(`data: ${JSON.stringify({ type: 'step', state: chunk.step.state, tool: chunk.step.action?.toolName ?? null })}\n\n`);
+        res.write(
+          `data: ${JSON.stringify({ type: 'step', state: chunk.step.state, tool: chunk.step.action?.toolName ?? null })}\n\n`
+        );
       } else if (chunk.type === 'done') {
         res.write(`data: ${JSON.stringify({ type: 'done', response: chunk.result.response })}\n\n`);
       }

package/@template-ai-native/src/agent/travel.controller.ts

@@ -7,7 +7,8 @@ import { Agent, Tool, Delegate, AgentService } from '@hazeljs/agent';
 @Agent({
   name: 'FactsAgent',
   description: 'Provides fun facts, cultural highlights, and travel tips about cities',
-  systemPrompt: 'You are a knowledgeable travel guide. Use your tools to provide interesting facts and tips about cities.',
+  systemPrompt:
+    'You are a knowledgeable travel guide. Use your tools to provide interesting facts and tips about cities.',
 })
 @Service()
 export class FactsAgent {
@@ -25,10 +26,26 @@ export class FactsAgent {
   async getCityFacts(input: { city: string }) {
     // In real app, call a travel/facts API or use a knowledge base
     const facts: Record<string, { fact: string; tip: string; bestTime: string }> = {
-      paris:   { fact: 'Paris has more than 470 parks and gardens.', tip: 'Buy a Paris Museum Pass to skip long queues.', bestTime: 'April–June or September–November' },
-      tokyo:   { fact: 'Tokyo has the world\'s busiest pedestrian crossing at Shibuya.', tip: 'Get a Suica card for seamless transit across the city.', bestTime: 'March–May (cherry blossom) or October–November' },
-      london:  { fact: 'London has over 170 museums, most of which are free.', tip: 'The Oyster card gives the cheapest fares on public transport.', bestTime: 'May–September for mild weather' },
-      newyork: { fact: 'New York City has 468 subway stations — the most in the world.', tip: 'Walk the High Line for great views and free art installations.', bestTime: 'April–June or September–November' },
+      paris: {
+        fact: 'Paris has more than 470 parks and gardens.',
+        tip: 'Buy a Paris Museum Pass to skip long queues.',
+        bestTime: 'April–June or September–November',
+      },
+      tokyo: {
+        fact: "Tokyo has the world's busiest pedestrian crossing at Shibuya.",
+        tip: 'Get a Suica card for seamless transit across the city.',
+        bestTime: 'March–May (cherry blossom) or October–November',
+      },
+      london: {
+        fact: 'London has over 170 museums, most of which are free.',
+        tip: 'The Oyster card gives the cheapest fares on public transport.',
+        bestTime: 'May–September for mild weather',
+      },
+      newyork: {
+        fact: 'New York City has 468 subway stations — the most in the world.',
+        tip: 'Walk the High Line for great views and free art installations.',
+        bestTime: 'April–June or September–November',
+      },
     };
 
     const key = input.city.toLowerCase().replace(/\s+/g, '');
@@ -49,7 +66,8 @@ export class FactsAgent {
 @Agent({
   name: 'TravelAgent',
   description: 'Travel planning assistant that checks weather and provides itinerary advice',
-  systemPrompt: 'You are a travel planner. Use your tools to check weather and forecasts for cities, then provide helpful travel advice based on the conditions.',
+  systemPrompt:
+    'You are a travel planner. Use your tools to check weather and forecasts for cities, then provide helpful travel advice based on the conditions.',
 })
 @Service()
 export class TravelAgent {
@@ -59,7 +77,8 @@ export class TravelAgent {
   // The LLM sees it as a regular tool — agent-to-agent is completely transparent.
   @Delegate({
     agent: 'WeatherAgent',
-    description: 'Check weather conditions and forecasts for a city to inform travel recommendations',
+    description:
+      'Check weather conditions and forecasts for a city to inform travel recommendations',
     inputField: 'input',
   })
   async checkWeather(input: string): Promise<string> {
@@ -87,7 +106,7 @@ export class TravelAgent {
 export class TravelController {
   constructor(
     private readonly travelAgent: TravelAgent,
-    private readonly agentService: AgentService,
+    private readonly agentService: AgentService
   ) {}
 
   // Feature: Agent Delegation — TravelAgent delegates to WeatherAgent via @Delegate
@@ -107,7 +126,8 @@ export class TravelController {
     const supervisor = runtime.createSupervisor({
       name: 'travel-supervisor',
       workers: ['WeatherAgent', 'FactsAgent'],
-      systemPrompt: 'You are a travel planning supervisor. Route requests to WeatherAgent for weather/forecast questions and to FactsAgent for city facts, tips, and general travel advice. Combine results when both are relevant.',
+      systemPrompt:
+        'You are a travel planning supervisor. Route requests to WeatherAgent for weather/forecast questions and to FactsAgent for city facts, tips, and general travel advice. Combine results when both are relevant.',
       maxRounds: 6,
     });
 

package/@template-ai-native/src/rag/rag.controller.ts

@@ -13,7 +13,7 @@ export class RAGService {
       apiKey: process.env.OPENAI_API_KEY!,
       model: 'text-embedding-3-small',
     });
-    
+
     // Initialize Prisma for PostgreSQL storage
     this.prisma = new PrismaClient();
   }
@@ -23,17 +23,17 @@ export class RAGService {
     const count = await this.prisma.document.count();
     console.log(`RAG Service initialized - PostgreSQL vector store ready with ${count} documents`);
   }
-  
+
   async onModuleDestroy() {
     await this.prisma.$disconnect();
   }
 
   async ingestDocument(content: string, metadata?: any) {
     console.log(`Ingesting document, content length: ${content.length}`);
-    
+
     // Generate embedding for the document
     const embedding = await this.embeddings.embed(content);
-    
+
     // Store in PostgreSQL
     const document = await this.prisma.document.create({
       data: {
@@ -46,32 +46,36 @@ export class RAGService {
         },
       },
     });
-    
+
     const totalDocuments = await this.prisma.document.count();
-    console.log(`Document ingested successfully. ID: ${document.id}, Total documents: ${totalDocuments}`);
-    
-    return { 
-      id: document.id, 
+    console.log(
+      `Document ingested successfully. ID: ${document.id}, Total documents: ${totalDocuments}`
+    );
+
+    return {
+      id: document.id,
       message: 'Document ingested successfully and stored in PostgreSQL',
-      totalDocuments
+      totalDocuments,
     };
   }
 
   async search(query: string, topK = 5) {
     const totalDocuments = await this.prisma.document.count();
     console.log(`RAG search requested for: "${query}". Total documents: ${totalDocuments}`);
-    
+
     // Generate embedding for the query
     const queryVector = await this.embeddings.embed(query);
-    
+
     // Perform vector similarity search using raw SQL for cosine similarity
     // Note: We don't select the embedding column to avoid deserialization issues
-    const results = await this.prisma.$queryRaw<Array<{
-      id: string;
-      content: string;
-      metadata: any;
-      similarity: number;
-    }>>`
+    const results = await this.prisma.$queryRaw<
+      Array<{
+        id: string;
+        content: string;
+        metadata: any;
+        similarity: number;
+      }>
+    >`
       SELECT 
         id,
         content,
@@ -81,22 +85,22 @@ export class RAGService {
       ORDER BY embedding <=> ${queryVector}::vector
       LIMIT ${topK}
     `;
-    
+
     console.log(`RAG search for "${query}" returned ${results.length} results`);
-    
-    return results.map(result => ({
+
+    return results.map((result) => ({
       id: result.id,
       content: result.content,
       score: result.similarity,
       metadata: result.metadata,
     }));
   }
-  
+
   async getDocumentCount() {
     const totalDocuments = await this.prisma.document.count();
     return { totalDocuments };
   }
-  
+
   async getAllDocuments() {
     const documents = await this.prisma.document.findMany({
       select: {
@@ -132,29 +136,29 @@ export class RAGController {
   @Get('documents')
   async getDocuments() {
     const stats = await this.ragService.getDocumentCount();
-    return { 
+    return {
       message: 'RAG service is ready - PostgreSQL vector store with persistent storage',
       ...stats,
       endpoints: {
         ingest: 'POST /rag/ingest - Add documents to PostgreSQL',
         search: 'POST /rag/search - Search documents with vector similarity',
         stats: 'GET /rag/stats - Get document count',
-        list: 'GET /rag/list - List all documents'
-      }
+        list: 'GET /rag/list - List all documents',
+      },
     };
   }
-  
+
   @Get('stats')
   async getStats() {
     return this.ragService.getDocumentCount();
   }
-  
+
   @Get('list')
   async listDocuments() {
     const documents = await this.ragService.getAllDocuments();
-    return { 
+    return {
       documents,
-      total: documents.length
+      total: documents.length,
     };
   }
 }

package/README.md

@@ -37,6 +37,7 @@ npm install --save-dev @hazeljs/cli
 ### Create a New Application
 
 **AI-Native Application (Recommended for AI Projects):**
+
 ```bash
 hazel g app my-ai-app --template=ai-native
 cd my-ai-app && npm install && cp .env.example .env && docker-compose up -d && npm run dev
@@ -45,17 +46,20 @@ cd my-ai-app && npm install && cp .env.example .env && docker-compose up -d && n
 Creates a complete AI-powered application with agents, RAG (PostgreSQL + pgvector), Redis, and Docker.
 
 **Skeleton app (quick start):**
+
 ```bash
 hazel g app my-app
 cd my-app && npm install && npm run dev
 ```
 
 **Full setup with interactive package selection:**
+
 ```bash
 hazel new my-app -i
 ```
 
 **Options:**
+
 - `-d, --dest <path>` - Destination path (default: current directory)
 - `-i, --interactive` - Interactive setup with package selection
 - `--template <template>` - Template to use (`ai-native` or `default`)
@@ -79,6 +83,7 @@ hazel add [package] [--setup] [--dev]
 Install a HazelJS package and show usage hints. Use `--setup` to also generate a minimal starter file.
 
 **Examples:**
+
 ```bash
 hazel add                  # Interactive package selection
 hazel add ai               # Install @hazeljs/ai
@@ -95,46 +100,48 @@ hazel g <type> <name> [--path <path>] [--dry-run] [--json]
 ```
 
 **Discover generators:**
+
 ```bash
 hazel g --list              # Human-readable list
 hazel g --list --list-json  # JSON output
 ```
 
 **Common options** (work the same for every generator):
+
 - `-p, --path <path>` - Where to generate (default: `src`)
 - `--dry-run` - Preview files without writing them
 - `--json` - Output result as JSON (`{ ok, created, nextSteps }`)
 
 #### Multi-File Generators
 
-| Generator | Alias | Description | Creates |
-|-----------|-------|-------------|---------|
-| `crud <name>` | — | Complete CRUD resource | controller + service + module + DTOs |
-| `module <name>` | `m` | Feature module | module + controller + service + DTOs |
-| `dto <name>` | `d` | Create & update DTOs | two DTO files |
-| `auth` | — | Auth module | JWT guard + service + controller + DTOs |
+| Generator       | Alias | Description            | Creates                                 |
+| --------------- | ----- | ---------------------- | --------------------------------------- |
+| `crud <name>`   | —     | Complete CRUD resource | controller + service + module + DTOs    |
+| `module <name>` | `m`   | Feature module         | module + controller + service + DTOs    |
+| `dto <name>`    | `d`   | Create & update DTOs   | two DTO files                           |
+| `auth`          | —     | Auth module            | JWT guard + service + controller + DTOs |
 
 #### Single-File Generators
 
-| Generator | Alias | Description |
-|-----------|-------|-------------|
-| `controller <name>` | `c` | REST controller with CRUD methods |
-| `service <name>` | `s` | Injectable service class |
-| `guard <name>` | `gu` | Route guard (e.g. auth) |
-| `interceptor <name>` | `i` | Request/response interceptor |
-| `middleware <name>` | `mw` | Express-style middleware |
-| `pipe <name>` | — | Validation/transform pipe |
-| `filter <name>` | `f` | Exception filter |
-| `repository <name>` | `repo` | Prisma repository |
-| `gateway <name>` | `ws` | WebSocket gateway |
-| `ai-service <name>` | `ai` | AI service with decorators |
-| `agent <name>` | — | AI agent with @Agent and @Tool |
-| `cache <name>` | — | Cache service with decorators |
-| `cron <name>` | `job` | Cron/scheduled job service |
-| `rag <name>` | — | RAG service |
-| `discovery <name>` | — | Service discovery setup |
-| `config` | — | Config module setup |
-| `serverless <name>` | `sls` | Serverless handler (Lambda/Cloud Function) |
+| Generator            | Alias  | Description                                |
+| -------------------- | ------ | ------------------------------------------ |
+| `controller <name>`  | `c`    | REST controller with CRUD methods          |
+| `service <name>`     | `s`    | Injectable service class                   |
+| `guard <name>`       | `gu`   | Route guard (e.g. auth)                    |
+| `interceptor <name>` | `i`    | Request/response interceptor               |
+| `middleware <name>`  | `mw`   | Express-style middleware                   |
+| `pipe <name>`        | —      | Validation/transform pipe                  |
+| `filter <name>`      | `f`    | Exception filter                           |
+| `repository <name>`  | `repo` | Prisma repository                          |
+| `gateway <name>`     | `ws`   | WebSocket gateway                          |
+| `ai-service <name>`  | `ai`   | AI service with decorators                 |
+| `agent <name>`       | —      | AI agent with @Agent and @Tool             |
+| `cache <name>`       | —      | Cache service with decorators              |
+| `cron <name>`        | `job`  | Cron/scheduled job service                 |
+| `rag <name>`         | —      | RAG service                                |
+| `discovery <name>`   | —      | Service discovery setup                    |
+| `config`             | —      | Config module setup                        |
+| `serverless <name>`  | `sls`  | Serverless handler (Lambda/Cloud Function) |
 
 **Serverless** also accepts `--platform <lambda|cloud-function>` (default: `lambda`).
 
@@ -302,8 +309,9 @@ hazel g service users --json
 ```
 
 The manifest is automatically generated during build and always reflects the current package version. It includes:
+
 - Complete command schemas with options and arguments
-- All available generators with their capabilities  
+- All available generators with their capabilities
 - Package registry for `hazel add` commands
 - JSON schema validation for agent tool-use
 
@@ -316,4 +324,4 @@ Apache-2.0 © [HazelJS](https://hazeljs.ai)
 - [Documentation](https://hazeljs.ai/docs/packages/cli)
 - [GitHub](https://github.com/hazel-js/hazeljs)
 - [Issues](https://github.com/hazel-js/hazeljs/issues)
-- [Discord](https://discord.gg/PxNBPzvQk7)
+- [Discord](https://discord.gg/PxNBPzvQk7)

package/cli-manifest.json

@@ -4,7 +4,7 @@
   "description": "Machine-readable manifest of all CLI commands and options for LLM agent tool-use",
   "cli": {
     "name": "hazel",
-    "version": "0.7.9",
+    "version": "0.8.1",
     "description": "CLI for generating HazelJS components and applications"
   },
   "commands": [