tpmjs/packages/tools/official/recipe-emit
Ajax Davis 5c9f1a1d0a chore: update dependencies with compatibility fixes
- Update all packages to latest versions via pnpm update --latest
- Downgrade Prisma 7 to 6 (v7 requires schema migration)
- Downgrade Tailwind CSS 4 to 3 (v4 requires PostCSS migration)
- Downgrade Storybook 10 to 8 (addons not available in v10)
- Pin cheerio to 1.0.0-rc.12 via pnpm override (type exports changed)
- Fix AI SDK tool definitions: parameters -> inputSchema
- Fix cheerio types in extract-meta and table-extract tools
- Add explicit type annotations to tool execute functions
- Migrate biome config to v2.3.11 schema

All type-checks, tests, and builds pass.
2026-01-09 22:49:41 +10:00
..
src feat: add 55 new business tools and improve existing implementations 2026-01-01 19:23:32 +10:00
CHANGELOG.md chore: version packages 2025-12-31 23:54:47 +10:00
package.json chore: update dependencies with compatibility fixes 2026-01-09 22:49:41 +10:00
README.md feat: add 100+ official TPMJS tools 2025-12-31 22:55:56 +10:00
tsconfig.json feat: add 100+ official TPMJS tools 2025-12-31 22:55:56 +10:00
tsup.config.ts feat: add 100+ official TPMJS tools 2025-12-31 22:55:56 +10:00

@tpmjs/tools-recipe-emit

Emits a recipe in standard format for workflow orchestration. Validates and formats workflow recipes with steps, inputs, and outputs.

Installation

npm install @tpmjs/tools-recipe-emit

Usage

import { recipeEmitTool } from '@tpmjs/tools-recipe-emit';

const result = await recipeEmitTool.execute({
  name: 'Data Processing Pipeline',
  steps: [
    {
      tool: 'fetchData',
      inputs: { url: 'https://api.example.com/data' },
      outputs: { rawData: 'string' },
      description: 'Fetch data from API',
    },
    {
      tool: 'transformData',
      inputs: { rawData: 'string' },
      outputs: { processedData: 'object' },
      description: 'Transform raw data',
    },
    {
      tool: 'saveData',
      inputs: { processedData: 'object' },
      outputs: { success: 'boolean' },
      description: 'Save processed data',
    },
  ],
  metadata: {
    author: 'John Doe',
    version: '1.0.0',
    description: 'A simple data processing pipeline',
    tags: ['data', 'pipeline', 'etl'],
  },
});

console.log(result);
// {
//   recipe: {
//     name: 'Data Processing Pipeline',
//     version: '1.0.0',
//     steps: [...],
//     metadata: {...}
//   },
//   format: 'tpmjs-recipe-v1',
//   stepCount: 3,
//   validation: {
//     isValid: true,
//     warnings: []
//   }
// }

Features

  • Validation: Validates recipe structure and warns about potential issues
  • Step Chaining: Detects missing connections between step outputs and inputs
  • Standard Format: Outputs recipes in the TPMJS standard format (tpmjs-recipe-v1)
  • Metadata Support: Includes author, version, tags, and custom metadata
  • Detailed Warnings: Provides actionable warnings for recipe improvement

Input Schema

{
  name: string;              // Recipe name
  steps: Array<{             // Workflow steps
    tool: string;            // Tool name to execute
    inputs: object;          // Input parameters
    outputs: object;         // Expected outputs
    description?: string;    // Optional step description
  }>;
  metadata?: {               // Optional metadata
    author?: string;
    version?: string;
    description?: string;
    tags?: string[];
    createdAt?: string;
  };
}

Output Schema

{
  recipe: {
    name: string;
    version: string;
    steps: RecipeStep[];
    metadata: RecipeMetadata;
  };
  format: string;            // Always 'tpmjs-recipe-v1'
  stepCount: number;         // Number of steps
  validation: {
    isValid: boolean;        // Whether recipe is valid
    warnings: string[];      // Validation warnings
  };
}

License

MIT