78c72b85f3
OpenAI was rejecting tool definitions with error "schema must be a JSON Schema of 'type: "object"'". This was caused by AI SDK v5 not properly converting Zod schemas to JSON Schema format. **Changes:** - Upgrade AI SDK from v5.0.104 to v6.0.0-beta.124 - Upgrade @ai-sdk/openai from v2.0.74 to v3.0.0-beta.22 - Upgrade Zod from v3.25.76 to v4.1.13 across all packages **AI SDK v6 breaking changes:** - Tool definition API: `parameters` renamed to `inputSchema` - Removed `aiTool()` wrapper - use plain object with description, inputSchema, execute - Streaming API: Use `textStream` async iterator instead of onChunk callback - Zod schemas now properly converted to JSON Schema for OpenAI **Zod v4 breaking changes:** - `z.record()` now requires two arguments: `z.record(keySchema, valueSchema)` - `z.enum()` params changed: `errorMap` removed, use `message` instead - Type system improvements require explicit type parameters - Fixed type errors in @tpmjs/env, @tpmjs/npm-client, @tpmjs/types **Files changed:** - apps/web/src/lib/ai-agent/tool-executor-agent.ts - Updated tool definition to use `inputSchema` instead of `parameters` - Removed `aiTool()` wrapper - Fixed streaming to use `textStream` iterator - packages/env/src/index.ts - Updated type constraint from `z.ZodRawShape` to `Record<string, z.ZodTypeAny>` - packages/npm-client/src/package.ts - Fixed `z.record()` calls to include both key and value schemas - Added type assertions for record indexing - packages/types/src/tpmjs.ts - Changed `errorMap` to `message` in z.enum() calls **Testing:** - ✅ Type-check passes - ✅ Production build succeeds - ✅ All routes compile correctly This fixes the tool execution error where OpenAI rejected tool schemas with invalid format. 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| src | ||
| CHANGELOG.md | ||
| package.json | ||
| README.md | ||
| tsconfig.json | ||
| tsup.config.ts | ||
@tpmjs/createblogpost
A tool for creating structured blog posts with frontmatter and metadata. Part of the TPMJS registry.
Installation
npm install @tpmjs/createblogpost
# or
pnpm add @tpmjs/createblogpost
# or
yarn add @tpmjs/createblogpost
Usage
import { createBlogPost } from '@tpmjs/createblogpost';
const post = await createBlogPost({
title: 'Getting Started with TypeScript',
author: 'John Doe',
content: 'TypeScript is a typed superset of JavaScript that compiles to plain JavaScript...',
tags: ['typescript', 'javascript', 'programming'],
excerpt: 'Learn the basics of TypeScript in this comprehensive guide',
format: 'markdown',
});
console.log(post.formattedOutput);
API
createBlogPost(options: BlogPostOptions): Promise<BlogPost>
Creates a structured blog post with frontmatter and metadata.
Options
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
title |
string |
Yes | - | The title of the blog post |
author |
string |
Yes | - | The author of the blog post |
content |
string |
Yes | - | The main content of the blog post |
tags |
string[] |
No | [] |
Array of tags for categorization |
format |
'markdown' | 'mdx' |
No | 'markdown' |
Output format for the blog post |
excerpt |
string |
No | - | Short excerpt or summary of the post |
publishDate |
Date |
No | new Date() |
Publication date |
Returns
Returns a BlogPost object with the following structure:
{
frontmatter: {
title: string;
author: string;
date: string; // ISO date format (YYYY-MM-DD)
tags: string[];
slug: string; // Auto-generated from title
wordCount: number; // Calculated from content
readingTime: number; // Estimated minutes to read
excerpt?: string;
};
content: string;
formattedOutput: string; // Complete post with frontmatter
}
Example Output
---
title: "Getting Started with TypeScript"
author: John Doe
date: 2025-11-28
slug: getting-started-with-typescript
tags: ["typescript", "javascript", "programming"]
excerpt: "Learn the basics of TypeScript in this comprehensive guide"
wordCount: 250
readingTime: 2
---
TypeScript is a typed superset of JavaScript that compiles to plain JavaScript...
Features
- Automatic slug generation from title
- Word count calculation
- Reading time estimation (200 words/min)
- Support for both Markdown and MDX formats
- Customizable frontmatter
- SEO-friendly metadata
Use Cases
- Static site generators (Next.js, Gatsby, Astro)
- Content management systems
- Blog platforms
- Documentation sites
- Automated content generation
License
MIT