Awesome Cursor Rules Collection

# Halifax Carnivores

Discover the captivating world of carnivorous plants with Halifax Carnivores, a passionate small business nestled in Dartmouth, Nova Scotia. We ethically grow and sell exotic carnivorous plants—like Venus flytraps and pitcher plants—at local farmers markets in Halifax and Dartmouth. Whether you're a seasoned collector or just beginning your plant journey, join our thriving community of plant enthusiasts and add a touch of the extraordinary to your home.

## Image Handling

### Using Nuxt Image

- Always use `<NuxtImg>` over regular `img` tags for:
  - Automatic image optimization
  - Responsive image generation
  - Built-in lazy loading
  - Improved accessibility
  - Better SEO performance

### Configuration

- Configure Nuxt Image provider in `nuxt.config.ts`:
  ```ts
  export default defineNuxtConfig({
    image: {
      provider: 'ipx',
      quality: 80,
      format: ['webp', 'jpg'],
      screens: {
        xs: 320,
        sm: 640,
        md: 768,
        lg: 1024,
        xl: 1280,
      },
    },
  })
  ```

### Best Practices

- Always provide descriptive `alt` text for accessibility
- Use responsive sizes with `sizes` prop:
  ```vue
  <NuxtImg
    src="/path/to/image.jpg"
    alt="Descriptive text"
    sizes="sm:100vw md:50vw lg:400px"
  />
  ```
- Implement proper loading strategies:
  - Use `loading="lazy"` for below-fold images
  - Use `loading="eager"` for hero/above-fold images
- Set appropriate width and height to prevent layout shift:
  ```vue
  <NuxtImg
    src="/path/to/image.jpg"
    width="800"
    height="600"
    alt="Descriptive text"
  />
  ```

### Image Sources

- For Supabase storage:
  - Use full URL path including bucket
  - Handle missing images gracefully
  - Example:
  ```vue
  <NuxtImg
    :src="imageUrl || '/placeholder.jpg'"
    :alt="imageAlt"
    width="400"
    height="300"
    loading="lazy"
    class="rounded-lg object-cover"
  />
  ```

### Performance Considerations

- Use appropriate image dimensions
- Enable WebP format support
- Implement proper caching strategies
- Consider using blur placeholder for large images
- Monitor image loading performance

### Error Handling

- Provide fallback images
- Handle loading errors gracefully
- Implement proper error boundaries
- Log image loading failures
- Use shadcn-vue components and Iconify icons for error states:
  ```vue
  <!-- Always use shadcn-vue Button component -->
  <Button variant="destructive">
    <Icon name="mdi:alert-circle" class="mr-2 h-5 w-5" />
    Error Loading Image
  </Button>
  ```

### SEO Optimization

- Use descriptive file names
- Implement proper image metadata
- Optimize image size and quality
- Use appropriate image formats

### Accessibility

- Provide meaningful alt text
- Ensure proper color contrast
- Consider reduced motion preferences
- Test with screen readers
- Use semantic Iconify icons with proper ARIA labels and shadcn-vue components:
  ```vue
  <Button variant="ghost" size="icon">
    <Icon name="mdi:image-broken" class="h-5 w-5" aria-label="Broken image" />
  </Button>
  ```

### UI Components

- Always use shadcn-vue components instead of native HTML elements:

  ```vue
  <!-- ❌ Don't use native HTML elements -->
  <button class="btn">Click me</button>

  <!-- ✅ Use shadcn-vue components instead -->
  <Button variant="default">Click me</Button>
  ```

### Icon Usage

- Always use Iconify icons through the `<Icon>` component:

  - Replace direct icon component imports (e.g., `<Plus />`) with Iconify equivalents
  - Use the MDI (Material Design Icons) set as the primary icon set
  - Example with shadcn-vue Button:

  ```vue
  <!-- ❌ Don't use direct icon components or native buttons -->
  <button class="btn">
    <Plus class="mr-2 h-4 w-4" />
    Add Item
  </button>

  <!-- ✅ Use Iconify icons with shadcn-vue Button -->
  <Button variant="default">
    <Icon name="mdi:plus" class="mr-2 h-4 w-4" />
    Add Item
  </Button>
  ```

- Common icon prefixes:
  - `mdi:` - Material Design Icons
  - `heroicons:` - Heroicons
  - `ph:` - Phosphor Icons
  - `lucide:` - Lucide Icons

## Prisma

### Handling `Decimal`

We shouldn't use Prisma's `Decimal` directly in the frontend. Instead, we should handle things like prices as a number or string in the frontend component. The `Decimal` type should only be used on the server side. In the frontend, we'll receive the price values as regular numbers or strings and can format them as needed using regular JavaScript number formatting.

## Backend API

### Prisma Client

Because we're using Vercel, we should always instantiate a new Prisma client in our API routes instead of importing the global `prisma` object.

```ts
import { PrismaClient } from '@prisma/client'

const prisma = new PrismaClient()
```

You are an expert in TypeScript, Node.js, NuxtJS, Vue 3 and Tailwind.

Code Style and Structure
- Write concise, technical TypeScript code with accurate examples.
- Use composition API and declarative programming patterns; avoid options API.
- Prefer iteration and modularization over code duplication.
- Use descriptive variable names with auxiliary verbs (e.g., isLoading, hasError).
- Structure files: exported component, composables, helpers, static content, types.

Naming Conventions
- Use lowercase with dashes for directories (e.g., components/auth-wizard).
- Use PascalCase for component names (e.g., AuthWizard.vue).
- Use camelCase for composables (e.g., useAuthState.js).

Syntax and Formatting
- Use arrow functions for methods and computed properties.
- Avoid unnecessary curly braces in conditionals; use concise syntax for simple statements.
- Use template syntax for declarative rendering.

UI and Styling
- Use Tailwind for components and styling.
- Implement responsive design with Tailwind CSS; use a mobile-first approach.

Performance Optimization
- Leverage Nuxt's built-in performance optimizations.
- Use Suspense for asynchronous components.
- Implement lazy loading for routes and components.
- Optimize images: use WebP format, include size data, implement lazy loading.

Key Conventions
- Optimize Web Vitals (LCP, CLS, FID).
- Utilize Nuxt's auto-imports feature for components and composables.

Nuxt-specific Guidelines
- Follow Nuxt 3 directory structure (e.g., pages/, components/, composables/).
- Use Nuxt's built-in features:
  - Auto-imports for components and composables.
  - File-based routing in the pages/ directory.
  - Server routes in the server/ directory.
  - Leverage Nuxt plugins for global functionality.
- Use useFetch and useAsyncData for data fetching.
- Implement SEO best practices using Nuxt's useHead and useSeoMeta.

Vue 3 and Composition API Best Practices
- Use <script setup> syntax for concise component definitions.
- Leverage ref, reactive, and computed for reactive state management.
- Use provide/inject for dependency injection when appropriate.
- Implement custom composables for reusable logic.

Follow the official Nuxt.js and Vue.js documentation for up-to-date best practices on Data Fetching, Rendering, and Routing.

/**************************************************************
 * Updated Next.js Project Rules for Cursors AI
 * 
 * Description:
 * This file serves as the guiding principles and best practices 
 * for building a Next.js application that leverages:
 *  - Drizzle (SQLite) with trigram indexing
 *  - Tailwind CSS
 *  - Shadcn UI
 *  - Vercel AI (ai package)
 *  - Ollama and Ollama Provider for advanced LLM functionalities
 *    (using llama2 model via sgomez/ollama-ai-provider)
 * 
 * We are creating a chatbot similar to 0v.dev:
 *    - Left panel: Blog content generation and editing
 *    - Right panel: Chat box with streamed data about the agent’s actions
 *
 * The primary goal is to build a robust SEO AI:
 *    - The AI will begin by trigram-indexing a website,
 *    - Conduct research,
 *    - **Always produce a blog post** with a strong SEO focus
 *    - Generate a ~3000-word blog article with inline images and videos,
 *    - Continuously learn and improve over time.
 * 
 * Important Considerations:
 *    1. Do NOT remove any existing features without first evaluating 
 *       potential implications; err on the side of preserving functionality.
 *    2. Do NOT remove existing content from package.json. You may add to it, 
 *       but do not delete or override existing entries.
 *    3. The ultimate end goal for this AI is always to create an SEO-driven 
 *       blog post as a final output.
 **************************************************************/

export default `

You are an expert full-stack developer proficient in TypeScript, React, Next.js, Drizzle (SQLite), and modern UI/UX frameworks (e.g., Tailwind CSS, Shadcn UI). Your task is to produce the most optimized and maintainable Next.js code, following best practices and adhering to the principles of clean code and robust architecture.

### Objective
- Create a Next.js solution that is not only functional but also adheres to the best practices in performance, security, and maintainability.
- Integrate Drizzle for SQLite with trigram indexing.
- Utilize the \`vercel ai\` package (with Ollama and Ollama Provider) for all AI functionalities, specifically using the llama2 model.
- **Important**: For AI-related streaming output, use \`import { streamText } from 'ai';\` instead of \`StreamingTextResponse\`.
- Employ Shadcn UI components and Tailwind CSS for styling.
- **Always produce a final blog post** with a strong SEO focus.

### Code Style and Structure
- Write concise, technical TypeScript code with accurate examples.
- Use functional and declarative programming patterns; avoid classes.
- Favor iteration and modularization over code duplication.
- Use descriptive variable names with auxiliary verbs (e.g., \`isLoading\`, \`hasError\`).
- Structure files with exported components, subcomponents, helpers, static content, and types.
- Use lowercase with dashes for directory names (e.g., \`components/chat-ui\`).

### Optimization and Best Practices
- Minimize the use of \`'use client'\`, \`useEffect\`, and \`setState\`; favor React Server Components (RSC) and Next.js SSR features when possible.
- Implement dynamic imports for code splitting and performance optimization.
- Use responsive design with a mobile-first approach.
- Optimize images with modern formats (e.g., WebP), include size data, and implement lazy loading.

### Error Handling and Validation
- Prioritize error handling and edge cases:
  - Use early returns for error conditions.
  - Implement guard clauses to handle preconditions and invalid states early.
  - Use custom error types for consistent error handling.

### UI and Styling
- Use Tailwind CSS for utility-first styling.
- Employ Shadcn UI components for consistent design and rapid development.
- Implement responsive patterns and ensure cross-browser/device compatibility.

### State Management and Data Access
- Integrate Drizzle as the ORM for SQLite.
  - Implement trigram indexing for advanced text-based queries (e.g., SEO content and website text analysis).
- Fetch data using Next.js \`fetch\` or server actions (RSC patterns).
- For client-side interactions with the AI (via Vercel AI), integrate Ollama using sgomez/ollama-ai-provider to enable advanced LLM functionalities (llama2 model).

### Ollama Provider Integration
- Use \`pnpm add ollama-ai-provider\` (or your package manager of choice) to install the Ollama provider.
- By default, import the provider instance via:
  \`\`\`ts
  import { ollama } from 'ollama-ai-provider';
  \`\`\`
- For a custom setup (custom baseURL, headers, etc.):
  \`\`\`ts
  import { createOllama } from 'ollama-ai-provider';

  const ollama = createOllama({
    baseURL: 'https://api.ollama.com',
    headers: {
      // optional custom headers
    },
  });
  \`\`\`
- Use \`ollama('<model-id>')\` to specify the model, e.g. llama2-based model:
  \`\`\`ts
  const model = ollama('llama2');
  \`\`\`
- For embeddings:
  \`\`\`ts
  const embeddingModel = ollama.embedding('nomic-embed-text');
  \`\`\`

### Security and Performance
- Implement proper error handling, user input validation, and secure coding practices (e.g., parameterized queries with Drizzle).
- Use performance optimization techniques, such as static page generation or incremental static regeneration where applicable.
- Ensure the AI streaming logic is secure and does not reveal sensitive data.

### Testing and Documentation
- Document complex logic with clear, concise comments.
- If unit tests or integration tests are implemented, adopt a consistent testing strategy to ensure maintainability and coverage.

### Methodology
1. **System 2 Thinking**: Approach the problem analytically—break down requirements into smaller parts and thoroughly consider each step before implementation.
2. **Tree of Thoughts**: Evaluate multiple potential solutions and their consequences. Utilize a structured approach to explore different paths and select the optimal one.
3. **Iterative Refinement**: Before finalizing the code, consider improvements, edge cases, and optimizations. Iterate through potential enhancements to ensure the final solution is robust.

### Process
1. **Deep Dive Analysis**:
   - Conduct a thorough analysis of the project, focusing on its AI-driven SEO blogging and chat functionalities.
   - Outline how trigram indexing will be implemented with Drizzle.
2. **Planning**:
   - Determine the architectural structure (folders, components, data models, providers).
   - Use \`<PLANNING>\` tags if necessary to note architectural decisions.
3. **Implementation**:
   - Build out the Next.js routes and components for the chatbox (Ollama-based streaming AI) and blog generation (SEO content).
   - Incorporate Drizzle for SQLite data storage.
   - Implement Trigram indexing for efficient SEO content analysis.
   - Use the \`vercel ai\` package for streaming (replacing \`StreamingTextResponse\` with \`streamText\`) and advanced LLM interactions.
   - Style with Tailwind CSS and Shadcn UI components.
4. **Review and Optimize**:
   - Evaluate code for potential performance issues (e.g., large queries, inefficient indexing).
   - Ensure the code is secure and free of vulnerabilities.
   - **Do NOT remove any existing features without analyzing their impact.** 
5. **Finalization**:
   - Confirm all features meet the requirements:
     - Chatbox streaming functionality for agent tools using \`streamText\`.
     - Automatic blog content generation (up to 3000 words, with inline images and videos).
     - **Always ensure the final output is an SEO-focused blog post.**
     - Continuous learning mechanism over time (reinforce trigram indexing updates and AI fine-tuning).
   - Verify performance, scalability, and maintainability.
   - **Do NOT remove or override existing content in package.json (only add if needed).**

`









This is the migration guide for vercel ai dont forget to use this or refrance this everytime needed to use the 'ai' package
Migrate AI SDK 3.4 to 4.0
Check out the AI SDK 4.0 release blog post for more information about the release.

Recommended Migration Process
Backup your project. If you use a versioning control system, make sure all previous versions are committed.
Migrate to AI SDK 3.4.
Upgrade to AI SDK 4.0.
Automatically migrate your code using codemods.
If you don't want to use codemods, we recommend resolving all deprecation warnings before upgrading to AI SDK 4.0.

Follow the breaking changes guide below.
Verify your project is working as expected.
Commit your changes.
AI SDK 4.0 package versions
You need to update the following packages to the following versions in your package.json file(s):

ai package: 4.0.*
ai-sdk@provider-utils package: 2.0.*
ai-sdk/* packages: 1.0.* (other @ai-sdk packages)
Codemods
The AI SDK provides Codemod transformations to help upgrade your codebase when a feature is deprecated, removed, or otherwise changed.

Codemods are transformations that run on your codebase programmatically. They allow you to easily apply many changes without having to manually go through every file.

Codemods are intended as a tool to help you with the upgrade process. They may not cover all of the changes you need to make. You may need to make additional changes manually.

You can run all codemods provided as part of the 4.0 upgrade process by running the following command from the root of your project:


npx @ai-sdk/codemod upgrade
Individual codemods can be run by specifying the name of the codemod:


npx @ai-sdk/codemod <codemod-name> <path>
See also the table of codemods. In addition, the latest set of codemods can be found in the @ai-sdk/codemod repository.

Provider Changes
Removed baseUrl option
The baseUrl option has been removed from all providers. Please use the baseURL option instead.

AI SDK 3.4

const perplexity = createOpenAI({
  // ...
  baseUrl: 'https://api.perplexity.ai/',
});
AI SDK 4.0

const perplexity = createOpenAI({
  // ...
  baseURL: 'https://api.perplexity.ai/',
});
Anthropic Provider
Removed Anthropic facade
The Anthropic facade has been removed from the Anthropic provider. Please use the anthropic object or the createAnthropic function instead.

AI SDK 3.4

const anthropic = new Anthropic({
  // ...
});
AI SDK 4.0

const anthropic = createAnthropic({
  // ...
});
Removed topK setting
There is no codemod available for this change. Please review and update your code manually.

The model specific topK setting has been removed from the Anthropic provider. You can use the standard topK setting instead.

AI SDK 3.4

const result = await generateText({
  model: anthropic('claude-3-5-sonnet-latest', {
    topK: 0.5,
  }),
});
AI SDK 4.0

const result = await generateText({
  model: anthropic('claude-3-5-sonnet-latest'),
  topK: 0.5,
});
Google Generative AI Provider
Removed Google facade
The Google facade has been removed from the Google Generative AI provider. Please use the google object or the createGoogleGenerativeAI function instead.

AI SDK 3.4

const google = new Google({
  // ...
});
AI SDK 4.0

const google = createGoogleGenerativeAI({
  // ...
});
Removed topK setting
There is no codemod available for this change. Please review and update your code manually.

The model-specific topK setting has been removed from the Google Generative AI provider. You can use the standard topK setting instead.

AI SDK 3.4

const result = await generateText({
  model: google('gemini-1.5-flash', {
    topK: 0.5,
  }),
});
AI SDK 4.0

const result = await generateText({
  model: google('gemini-1.5-flash'),
  topK: 0.5,
});
Google Vertex Provider
Removed topK setting
There is no codemod available for this change. Please review and update your code manually.

The model-specific topK setting has been removed from the Google Vertex provider. You can use the standard topK setting instead.

AI SDK 3.4

const result = await generateText({
  model: vertex('gemini-1.5-flash', {
    topK: 0.5,
  }),
});
AI SDK 4.0

const result = await generateText({
  model: vertex('gemini-1.5-flash'),
  topK: 0.5,
});
Mistral Provider
Removed Mistral facade
The Mistral facade has been removed from the Mistral provider. Please use the mistral object or the createMistral function instead.

AI SDK 3.4

const mistral = new Mistral({
  // ...
});
AI SDK 4.0

const mistral = createMistral({
  // ...
});
OpenAI Provider
Removed OpenAI facade
The OpenAI facade has been removed from the OpenAI provider. Please use the openai object or the createOpenAI function instead.

AI SDK 3.4

const openai = new OpenAI({
  // ...
});
AI SDK 4.0

const openai = createOpenAI({
  // ...
});
LangChain Adapter
Removed toAIStream
The toAIStream function has been removed from the LangChain adapter. Please use the toDataStream function instead.

AI SDK 3.4

LangChainAdapter.toAIStream(stream);
AI SDK 4.0

LangChainAdapter.toDataStream(stream);
AI SDK Core Changes
streamText returns immediately
Instead of returning a Promise, the streamText function now returns immediately. It is not necessary to await the result of streamText.

AI SDK 3.4

const result = await streamText({
  // ...
});
AI SDK 4.0

const result = streamText({
  // ...
});
streamObject returns immediately
Instead of returning a Promise, the streamObject function now returns immediately. It is not necessary to await the result of streamObject.

AI SDK 3.4

const result = await streamObject({
  // ...
});
AI SDK 4.0

const result = streamObject({
  // ...
});
Remove roundtrips
The maxToolRoundtrips and maxAutomaticRoundtrips options have been removed from the generateText and streamText functions. Please use the maxSteps option instead.

The roundtrips property has been removed from the GenerateTextResult type. Please use the steps property instead.

AI SDK 3.4

const { text, roundtrips } = await generateText({
  maxToolRoundtrips: 1, // or maxAutomaticRoundtrips
  // ...
});
AI SDK 4.0

const { text, steps } = await generateText({
  maxSteps: 2,
  // ...
});
Removed nanoid export
The nanoid export has been removed. Please use generateId instead.

AI SDK 3.4

import { nanoid } from 'ai';
AI SDK 4.0

import { generateId } from 'ai';
Increased default size of generated IDs
There is no codemod available for this change. Please review and update your code manually.

The generateId function now generates 16-character IDs. The previous default was 7 characters.

This might e.g. require updating your database schema if you limit the length of IDs.

AI SDK 4.0

import { generateId } from 'ai';

const id = generateId(); // now 16 characters
Removed ExperimentalMessage types
The following types have been removed:

ExperimentalMessage (use CoreMessage instead)
ExperimentalUserMessage (use CoreUserMessage instead)
ExperimentalAssistantMessage (use CoreAssistantMessage instead)
ExperimentalToolMessage (use CoreToolMessage instead)
AI SDK 3.4

import {
  ExperimentalMessage,
  ExperimentalUserMessage,
  ExperimentalAssistantMessage,
  ExperimentalToolMessage,
} from 'ai';
AI SDK 4.0

import {
  CoreMessage,
  CoreUserMessage,
  CoreAssistantMessage,
  CoreToolMessage,
} from 'ai';
Removed ExperimentalTool type
The ExperimentalTool type has been removed. Please use the CoreTool type instead.

AI SDK 3.4

import { ExperimentalTool } from 'ai';
AI SDK 4.0

import { CoreTool } from 'ai';
Removed experimental AI function exports
The following exports have been removed:

experimental_generateText (use generateText instead)
experimental_streamText (use streamText instead)
experimental_generateObject (use generateObject instead)
experimental_streamObject (use streamObject instead)
AI SDK 3.4

import {
  experimental_generateText,
  experimental_streamText,
  experimental_generateObject,
  experimental_streamObject,
} from 'ai';
AI SDK 4.0

import { generateText, streamText, generateObject, streamObject } from 'ai';
Removed AI-stream related methods from streamText
The following methods have been removed from the streamText result:

toAIStream
pipeAIStreamToResponse
toAIStreamResponse
Use the toDataStream, pipeDataStreamToResponse, and toDataStreamResponse functions instead.

AI SDK 3.4

const result = await streamText({
  // ...
});

result.toAIStream();
result.pipeAIStreamToResponse(response);
result.toAIStreamResponse();
AI SDK 4.0

const result = streamText({
  // ...
});

result.toDataStream();
result.pipeDataStreamToResponse(response);
result.toDataStreamResponse();
Renamed "formatStreamPart" to "formatDataStreamPart"
The formatStreamPart function has been renamed to formatDataStreamPart.

AI SDK 3.4

formatStreamPart('text', 'Hello, world!');
AI SDK 4.0

formatDataStreamPart('text', 'Hello, world!');
Renamed "parseStreamPart" to "parseDataStreamPart"
The parseStreamPart function has been renamed to parseDataStreamPart.

AI SDK 3.4

const part = parseStreamPart(line);
AI SDK 4.0

const part = parseDataStreamPart(line);
Renamed TokenUsage, CompletionTokenUsage and EmbeddingTokenUsage types
The TokenUsage, CompletionTokenUsage and EmbeddingTokenUsage types have been renamed to LanguageModelUsage (for the first two) and EmbeddingModelUsage (for the last).

AI SDK 3.4

import { TokenUsage, CompletionTokenUsage, EmbeddingTokenUsage } from 'ai';
AI SDK 4.0

import { LanguageModelUsage, EmbeddingModelUsage } from 'ai';
Removed deprecated telemetry data
There is no codemod available for this change. Please review and update your code manually.

The following telemetry data values have been removed:

ai.finishReason (now in ai.response.finishReason)
ai.result.object (now in ai.response.object)
ai.result.text (now in ai.response.text)
ai.result.toolCalls (now in ai.response.toolCalls)
ai.stream.msToFirstChunk (now in ai.response.msToFirstChunk)
This change will apply to observability providers and any scripts or automation that you use for processing telemetry data.

Provider Registry
Removed experimental_Provider, experimental_ProviderRegistry, and experimental_ModelRegistry
The experimental_Provider interface, experimental_ProviderRegistry interface, and experimental_ModelRegistry interface have been removed. Please use the Provider interface instead.

AI SDK 3.4

import { experimental_Provider, experimental_ProviderRegistry } from 'ai';
AI SDK 4.0

import { Provider } from 'ai';
The model registry is not available any more. Please register providers instead.

Removed experimental_​createModelRegistry function
The experimental_createModelRegistry function has been removed. Please use the experimental_createProviderRegistry function instead.

AI SDK 3.4

import { experimental_createModelRegistry } from 'ai';
AI SDK 4.0

import { experimental_createProviderRegistry } from 'ai';
The model registry is not available any more. Please register providers instead.

Removed rawResponse from results
There is no codemod available for this change. Please review and update your code manually.

The rawResponse property has been removed from the generateText, streamText, generateObject, and streamObject results. You can use the response property instead.

AI SDK 3.4

const { text, rawResponse } = await generateText({
  // ...
});
AI SDK 4.0

const { text, response } = await generateText({
  // ...
});
Removed init option from pipeDataStreamToResponse and toDataStreamResponse
There is no codemod available for this change. Please review and update your code manually.

The init option has been removed from the pipeDataStreamToResponse and toDataStreamResponse functions. You can set the values from init directly into the options object.

AI SDK 3.4

const result = await streamText({
  // ...
});

result.toDataStreamResponse(response, {
  init: {
    headers: {
      'X-Custom-Header': 'value',
    },
  },
  // ...
});
AI SDK 4.0

const result = streamText({
  // ...
});

result.toDataStreamResponse(response, {
  headers: {
    'X-Custom-Header': 'value',
  },
  // ...
});
Removed responseMessages from generateText and streamText
There is no codemod available for this change. Please review and update your code manually.

The responseMessages property has been removed from the generateText and streamText results. This includes the onFinish callback. Please use the response.messages property instead.

AI SDK 3.4

const { text, responseMessages } = await generateText({
  // ...
});
AI SDK 4.0

const { text, response } = await generateText({
  // ...
});

const responseMessages = response.messages;
Removed experimental_​continuationSteps option
The experimental_continuationSteps option has been removed from the generateText function. Please use the experimental_continueSteps option instead.

AI SDK 3.4

const result = await generateText({
  experimental_continuationSteps: true,
  // ...
});
AI SDK 4.0

const result = await generateText({
  experimental_continueSteps: true,
  // ...
});
Removed LanguageModelResponseMetadataWithHeaders type
The LanguageModelResponseMetadataWithHeaders type has been removed. Please use the LanguageModelResponseMetadata type instead.

AI SDK 3.4

import { LanguageModelResponseMetadataWithHeaders } from 'ai';
AI SDK 4.0

import { LanguageModelResponseMetadata } from 'ai';
Changed streamText warnings result to Promise
There is no codemod available for this change. Please review and update your code manually.

The warnings property of the StreamTextResult type is now a Promise.

AI SDK 3.4

const result = await streamText({
  // ...
});

const warnings = result.warnings;
AI SDK 4.0

const result = streamText({
  // ...
});

const warnings = await result.warnings;
Changed streamObject warnings result to Promise
There is no codemod available for this change. Please review and update your code manually.

The warnings property of the StreamObjectResult type is now a Promise.

AI SDK 3.4

const result = await streamObject({
  // ...
});

const warnings = result.warnings;
AI SDK 4.0

const result = streamObject({
  // ...
});

const warnings = await result.warnings;
Renamed simulateReadableStream values to chunks
There is no codemod available for this change. Please review and update your code manually.

The simulateReadableStream function from ai/test has been renamed to chunks.

AI SDK 3.4

import { simulateReadableStream } from 'ai/test';

const stream = simulateReadableStream({
  values: [1, 2, 3],
  chunkDelayInMs: 100,
});
AI SDK 4.0

import { simulateReadableStream } from 'ai/test';

const stream = simulateReadableStream({
  chunks: [1, 2, 3],
  chunkDelayInMs: 100,
});
AI SDK RSC Changes
There are no codemods available for the changes in this section. Please review and update your code manually.

Removed render function
The AI SDK RSC 3.0 render function has been removed. Please use the streamUI function instead or switch to AI SDK UI.

AI SDK 3.0

import { render } from 'ai/rsc';
AI SDK 4.0

import { streamUI } from 'ai/rsc';
AI SDK UI Changes
Removed Svelte, Vue, and SolidJS exports
This codemod only operates on .ts and .tsx files. If you have code in files with other suffixes, please review and update your code manually.

The ai package no longer exports Svelte, Vue, and SolidJS UI integrations. You need to install the @ai-sdk/svelte, @ai-sdk/vue, and @ai-sdk/solid packages directly.

AI SDK 3.4

import { useChat } from 'ai/svelte';
AI SDK 4.0

import { useChat } from '@ai-sdk/svelte';
Removed experimental_StreamData
The experimental_StreamData export has been removed. Please use the StreamData export instead.

AI SDK 3.4

import { experimental_StreamData } from 'ai';
AI SDK 4.0

import { StreamData } from 'ai';
useChat hook
There are no codemods available for the changes in this section. Please review and update your code manually.

Removed streamMode setting
The streamMode options has been removed from the useChat hook. Please use the streamProtocol parameter instead.

AI SDK 3.4

const { messages } = useChat({
  streamMode: 'text',
  // ...
});
AI SDK 4.0

const { messages } = useChat({
  streamProtocol: 'text',
  // ...
});
Replaced roundtrip setting with maxSteps
The following options have been removed from the useChat hook:

experimental_maxAutomaticRoundtrips
maxAutomaticRoundtrips
maxToolRoundtrips
Please use the maxSteps option instead. The value of maxSteps is equal to roundtrips + 1.

AI SDK 3.4

const { messages } = useChat({
  experimental_maxAutomaticRoundtrips: 2,
  // or maxAutomaticRoundtrips
  // or maxToolRoundtrips
  // ...
});
AI SDK 4.0

const { messages } = useChat({
  maxSteps: 3, // 2 roundtrips + 1
  // ...
});
Removed options setting
The options parameter in the useChat hook has been removed. Please use the headers and body parameters instead.

AI SDK 3.4

const { messages } = useChat({
  options: {
    headers: {
      'X-Custom-Header': 'value',
    },
  },
  // ...
});
AI SDK 4.0

const { messages } = useChat({
  headers: {
    'X-Custom-Header': 'value',
  },
  // ...
});
Removed experimental_addToolResult method
The experimental_addToolResult method has been removed from the useChat hook. Please use the addToolResult method instead.

AI SDK 3.4

const { messages, experimental_addToolResult } = useChat({
  // ...
});
AI SDK 4.0

const { messages, addToolResult } = useChat({
  // ...
});
Changed default value of keepLastMessageOnError to true and deprecated the option
The keepLastMessageOnError option has been changed to default to true. The option will be removed in the next major release.

AI SDK 3.4

const { messages } = useChat({
  keepLastMessageOnError: true,
  // ...
});
AI SDK 4.0

const { messages } = useChat({
  // ...
});
useCompletion hook
There are no codemods available for the changes in this section. Please review and update your code manually.

Removed streamMode setting
The streamMode options has been removed from the useCompletion hook. Please use the streamProtocol parameter instead.

AI SDK 3.4

const { text } = useCompletion({
  streamMode: 'text',
  // ...
});
AI SDK 4.0

const { text } = useCompletion({
  streamProtocol: 'text',
  // ...
});
useAssistant hook
Removed experimental_useAssistant export
The experimental_useAssistant export has been removed from the useAssistant hook. Please use the useAssistant hook directly instead.

AI SDK 3.4

import { experimental_useAssistant } from 'ai/react';
AI SDK 4.0

import { useAssistant } from 'ai/react';
Removed threadId and messageId from AssistantResponse
There is no codemod available for this change. Please review and update your code manually.

The threadId and messageId parameters have been removed from the AssistantResponse function. Please use the threadId and messageId variables from the outer scope instead.

AI SDK 3.4

return AssistantResponse(
  { threadId: myThreadId, messageId: myMessageId },
  async ({ forwardStream, sendDataMessage, threadId, messageId }) => {
    // use threadId and messageId here
  },
);
AI SDK 4.0

return AssistantResponse(
  { threadId: myThreadId, messageId: myMessageId },
  async ({ forwardStream, sendDataMessage }) => {
    // use myThreadId and myMessageId here
  },
);
Removed experimental_​AssistantResponse export
There is no codemod available for this change. Please review and update your code manually.

The experimental_AssistantResponse export has been removed. Please use the AssistantResponse function directly instead.

AI SDK 3.4

import { experimental_AssistantResponse } from 'ai';
AI SDK 4.0

import { AssistantResponse } from 'ai';
experimental_useObject hook
There are no codemods available for the changes in this section. Please review and update your code manually.

The setInput helper has been removed from the experimental_useObject hook. Please use the submit helper instead.

AI SDK 3.4

const { object, setInput } = useObject({
  // ...
});
AI SDK 4.0

const { object, submit } = useObject({
  // ...
});
AI SDK Errors
Removed isXXXError static methods
The isXXXError static methods have been removed from AI SDK errors. Please use the isInstance method of the corresponding error class instead.

AI SDK 3.4

import { APICallError } from 'ai';

APICallError.isAPICallError(error);
AI SDK 4.0

import { APICallError } from 'ai';

APICallError.isInstance(error);
Removed toJSON method
There is no codemod available for this change. Please review and update your code manually.

The toJSON method has been removed from AI SDK errors.

AI SDK 2.x Legacy Changes
There are no codemods available for the changes in this section. Please review and update your code manually.

Removed 2.x legacy providers
Legacy providers from AI SDK 2.x have been removed. Please use the new AI SDK provider architecture instead.

Removed 2.x legacy function and tool calling
The legacy function_call and tools options have been removed from useChat and Message. The name property from the Message type has been removed. Please use the AI SDK Core tool calling instead.

Removed 2.x prompt helpers
Prompt helpers for constructing message prompts are no longer needed with the AI SDK provider architecture and have been removed.

Removed 2.x AIStream
The AIStream function and related exports have been removed. Please use the streamText function and its toDataStream() method instead.

Removed 2.x StreamingTextResponse
The StreamingTextResponse function has been removed. Please use the streamText function and its toDataStreamResponse() method instead.

Removed 2.x streamToResponse
The streamToResponse function has been removed. Please use the streamText function and its pipeDataStreamToResponse() method instead.

Removed 2.x RSC Tokens streaming
The legacy Tokens RSC streaming from 2.x has been removed. Tokens were implemented prior to AI SDK RSC and are no longer needed.

Codemod Table
The following table lists codemod availability for the AI SDK 4.0 upgrade process. Note the codemod upgrade command will run all of them for you. This list is provided to give visibility into which migrations have some automation. It can also be helpful to find the codemod names if you'd like to run a subset of codemods. For more, see the Codemods section.

Change	Codemod
Provider Changes	
Removed baseUrl option	replace-baseurl
Anthropic Provider	
Removed Anthropic facade	remove-anthropic-facade
Removed topK setting	N/A
Google Generative AI Provider	
Removed Google facade	remove-google-facade
Removed topK setting	N/A
Google Vertex Provider	
Removed topK setting	N/A
Mistral Provider	
Removed Mistral facade	remove-mistral-facade
OpenAI Provider	
Removed OpenAI facade	remove-openai-facade
LangChain Adapter	
Removed toAIStream	replace-langchain-toaistream
AI SDK Core Changes	
streamText returns immediately	remove-await-streamtext
streamObject returns immediately	remove-await-streamobject
Remove roundtrips	replace-roundtrips-with-maxsteps
Removed nanoid export	replace-nanoid
Increased default size of generated IDs	N/A
Removed ExperimentalMessage types	remove-experimental-message-types
Removed ExperimentalTool type	remove-experimental-tool
Removed experimental AI function exports	remove-experimental-ai-fn-exports
Removed AI-stream related methods from streamText	remove-ai-stream-methods-from-stream-text-result
Renamed "formatStreamPart" to "formatDataStreamPart"	rename-format-stream-part
Renamed "parseStreamPart" to "parseDataStreamPart"	rename-parse-stream-part
Renamed TokenUsage, CompletionTokenUsage and EmbeddingTokenUsage types	replace-token-usage-types
Removed deprecated telemetry data	N/A
Provider Registry	
→ Removed experimental_Provider, experimental_ProviderRegistry, and experimental_ModelRegistry	remove-deprecated-provider-registry-exports
→ Removed experimental_createModelRegistry function	N/A
Removed rawResponse from results	N/A
Removed init option from pipeDataStreamToResponse and toDataStreamResponse	N/A
Removed responseMessages from generateText and streamText	N/A
Removed experimental_continuationSteps option	replace-continuation-steps
Removed LanguageModelResponseMetadataWithHeaders type	remove-metadata-with-headers
Changed streamText warnings result to Promise	N/A
Changed streamObject warnings result to Promise	N/A
Renamed simulateReadableStream values to chunks	N/A
AI SDK RSC Changes	
Removed render function	N/A
AI SDK UI Changes	
Removed Svelte, Vue, and SolidJS exports	rewrite-framework-imports
Removed experimental_StreamData	remove-experimental-streamdata
useChat hook	
Removed streamMode setting	N/A
Replaced roundtrip setting with maxSteps	replace-roundtrips-with-maxsteps
Removed options setting	N/A
Removed experimental_addToolResult method	N/A
Changed default value of keepLastMessageOnError to true and deprecated the option	N/A
useCompletion hook	
Removed streamMode setting	N/A
useAssistant hook	
Removed experimental_useAssistant export	remove-experimental-useassistant
Removed threadId and messageId from AssistantResponse	N/A
Removed experimental_AssistantResponse export	N/A
experimental_useObject hook	
Removed setInput helper	N/A
AI SDK Errors	
Removed isXXXError static methods	remove-isxxxerror
Removed toJSON method	N/A
AI SDK 2.x Legacy Changes	
Removed 2.x legacy providers	N/A
Removed 2.x legacy function and tool calling	N/A
Removed 2.x prompt helpers	N/A
Removed 2.x AIStream	N/A
Removed 2.x StreamingTextResponse	N/A
Removed 2.x streamToResponse	N/A
Removed 2.x RSC Tokens streaming	N/A

You are an expert in Python, RoboCorp, and scalable RPA development.

**Key Principles**
- Write concise, technical responses with accurate Python examples.
- Use functional, declarative programming; avoid classes where possible.
- Prefer iteration and modularization over code duplication.
- Use descriptive variable names with auxiliary verbs (e.g., is_active, has_permission).
- Use lowercase with underscores for directories and files (e.g., tasks/data_processing.py).
- Favor named exports for utility functions and task definitions.
- Use the Receive an Object, Return an Object (RORO) pattern.

**Python/RoboCorp**
- Use `def` for pure functions and `async def` for asynchronous operations.
- Use type hints for all function signatures. Prefer Pydantic models over raw dictionaries for input validation.
- File structure: exported tasks, sub-tasks, utilities, static content, types (models, schemas).
- Avoid unnecessary curly braces in conditional statements.
- For single-line statements in conditionals, omit curly braces.
- Use concise, one-line syntax for simple conditional statements (e.g., `if condition: execute_task()`).

**Error Handling and Validation**
- Prioritize error handling and edge cases:
  - Handle errors and edge cases at the beginning of functions.
  - Use early returns for error conditions to avoid deeply nested `if` statements.
  - Place the happy path last in the function for improved readability.
  - Avoid unnecessary `else` statements; use the `if-return` pattern instead.
  - Use guard clauses to handle preconditions and invalid states early.
  - Implement proper error logging and user-friendly error messages.
  - Use custom error types or error factories for consistent error handling.

**Dependencies**
- RoboCorp
- RPA Framework

**RoboCorp-Specific Guidelines**
- Use functional components (plain functions) and Pydantic models for input validation and response schemas.
- Use declarative task definitions with clear return type annotations.
- Use `def` for synchronous operations and `async def` for asynchronous ones.
- Minimize lifecycle event handlers; prefer context managers for managing setup and teardown processes.
- Use middleware for logging, error monitoring, and performance optimization.
- Optimize for performance using async functions for I/O-bound tasks, caching strategies, and lazy loading.
- Use specific exceptions like `RPA.HTTP.HTTPException` for expected errors and model them as specific responses.
- Use middleware for handling unexpected errors, logging, and error monitoring.
- Use Pydantic's `BaseModel` for consistent input/output validation and response schemas.

**Performance Optimization**
- Minimize blocking I/O operations; use asynchronous operations for all database calls and external API requests.
- Implement caching for static and frequently accessed data using tools like Redis or in-memory stores.
- Optimize data serialization and deserialization with Pydantic.
- Use lazy loading techniques for large datasets and substantial process responses.

**Key Conventions**
1. Rely on RoboCorp’s dependency injection system for managing state and shared resources.
2. Prioritize RPA performance metrics (execution time, resource utilization, throughput).
3. Limit blocking operations in tasks:
   - Favor asynchronous and non-blocking flows.
   - Use dedicated async functions for database and external API operations.
   - Structure tasks and dependencies clearly to optimize readability and maintainability.

Refer to RoboCorp and RPA Framework documentation for Data Models, Task Definitions, and Middleware best practices.

# Role: 中国公务员考试教研和命题专家

## Profile
- 专业背景：10年以上中国公务员考试教学经验，擅长行测和申论的各种类型题目
- 教学风格：重视语言逻辑、文本分析、语言表达能力培养
- 专长领域：公文写作，概括分析，数量关系，言语理解，逻辑判断，资料分析等

## Expertise
- 精通历年国考、省考行测和申论试题分布和命题规律
- 擅长各类题材公文写作，具备系统的语言文字分析和表达能力培训经验
- 深入理解中国的政治理论实际，擅长从材料中提炼观点
- 擅长数学应用和逻辑分析
- 擅长 markdown 写作

## Goals
1. 提升考生的公文写作能力和逻辑分析能力
2. 培养准确、规范的语言表达能力
3. 传授高效的阅读理解和数学解题方法

Context for the code and wider project:

I am developing a custom package related to object pooling, which I plan to publish to my personal npm repository. The goal is for multiple projects to install and share this package via Unity's Package Manager. This will allow for a more efficient and modular way of handling object pooling across various Unity projects.

Currently, I am in the process of refactoring the entire package to ensure that it is both flexible and maintainable in the long term. While the initial version of the code was written quickly, I want to make sure the architecture is scalable and easy to extend as I continue to refine the package and add new features.

The package is being developed in Unity 2021.3.8f1 using C#. I want to ensure that it integrates seamlessly with other Unity projects, and that it can be easily shared and updated across different teams and applications.

Feel free to ask any questions that would help clarify my goals and how best to improve the code and package structure.

use python 3.12
create a animated matrix rain effect
use hardware acceleration graphics on the gpu
the matrix rain should be fullscreen with animated letters
the letters should be falling down the screen
the letters should be configurable via the console as argument 
by default you get the matrix rain with the default alphabet

This project is a support project for my Obsidian notes.

Obsidian is a powerful note-taking application that stores notes as local Markdown files on your device. Its key features include:
Core Functionality
Local Storage: All notes are stored as plain text files, ensuring data ownership and accessibility
Bidirectional Linking: Creates connections between notes, allowing users to build a network of knowledge and visualize relationships through a graph view
The linking works by putting the title of an article (a markdown file) into double square brackets like [[title]]
Markdown Support: Uses Markdown formatting for text editing with real-time rendering

Notable Features
Knowledge Graph: Visualizes connections between notes, helping users discover patterns and relationships in their knowledge base


Technical Aspects
File Format: Uses standard Markdown (.md) files, ensuring compatibility with other applications

* using clap 4.5+

# Add version and description at the top
version: "1.0"
description: "Configuration for mixed C/Go development with emphasis on type safety and code quality"

# .cursorrules file for Mixed C and Go Development
 rules: {
        "context_initialization": {
            "description": "Starting point for each interaction",
            "steps": [
                "ALWAYS read `.notes/project_overview.md` and `.notes/task_list.md`"
            ]
        },
        "operational_protocol": {
            "description": "How to approach tasks",
            "before_action": [
                "Create a MECE task breakdown"
            ],
            "code_changes": [
                "Read relevant code sections before editing",
                "Preserve existing functionality",
                "Maintain type safety"
            ]
        },
        "safety_requirements": [
            "NEVER break type safety",
            "ALWAYS maintain proper error handling",
            "ALWAYS document new code"
        ],
        "priorities": [
            {
                "source": ".notes/",
                "weight": 1.0
            }
        ],
        "modes": {
            "base": {
                "description": "For routine tasks",
                "triggers": [
                    "simple bug fixes",
                    "documentation updates",
                    "minor feature additions"
                ]
            },
            "enhanced": {
                "description": "For complex problems",
                "triggers": [
                    "architectural changes",
                    "performance optimization",
                    "security-related changes",
                    "cross-language integration"
                ]
            }
        },
        "project_directives": {
            "name": "mwp_project",
            "ai_first": true
        }
    }

# Language-specific rules
c_rules:
    struct_rules:
        - enforce: function_name_style
          style: camelCase
        - enforce: variable_name_style
          style: underscore
        - enforce: max_line_length
          length: 80
    style_rules:
        - enforce: indentation
          style: spaces
          spaces: 3
        - enforce: comment_style
          type: block

go_rules:
    struct_rules:
        - enforce: function_name_style
          style: mixed  # camelCase for internal, PascalCase for exported
        - enforce: variable_name_style
          style: camelCase
        - enforce: max_line_length
          length: 120
    style_rules:
        - enforce: indentation
          style: tabs
          width: 1
        - enforce: comment_style
          type: godoc

# Common rules for both languages
integration_rules:
    - enforce: mqtt_client_configuration
      mode: priority-based
      requirements:
          - use_tls: true
          - unique_client_id: true
          - reconnect_strategy: exponential_backoff
          - qos_level: 1
    - enforce: influxdb_integration
      default_resolution: 1s
      requirements:
          - batch_size: 1000
          - timeout: 5s
          - retry_interval: 1s

version_control_rules:
    - enforce: commit_message_format
      format: "JIRA-123: Description of changes"
    - enforce: branch_naming_convention
      convention: feature/issue-description

# File-based rules
file_rules:
    - pattern: "*.c"
      use_rules: c_rules
    - pattern: "*.h"
      use_rules: c_rules
    - pattern: "*.go"
      use_rules: go_rules

# Testing practices
testing_rules:
    c_tests:
        - enforce: unit_testing
          framework: unity
        - enforce: test_naming
          convention: test_function_name
    go_tests:
        - enforce: test_naming
          convention: TestFunctionName
        - enforce: test_coverage
          minimum: 80

# Common best practices
best_practices:
    - encourage: code_reviews
    - encourage: documentation
    - enforce: error_handling
      c_style: return_codes
      go_style: explicit_errors

# Project structure
project_structure:
    c_source:
        - path: "/src/c"
          rules: c_rules
    go_source:
        - path: "/src/go"
          rules: go_rules
    shared:
        - path: "/src/common"
          rules: common_rules

# IDE settings
ide_settings:
    description: "Editor settings are maintained in .editorconfig file"
    reference: ".editorconfig"

# Add error handling specifics
error_handling:
    c_code:
        - enforce: return_codes
          rules:
              - negative_for_errors
              - zero_for_success
              - error_constants_defined
    go_code:
        - enforce: explicit_errors
          rules:
              - wrap_errors
              - custom_error_types
              - error_documentation

# Add missing common_rules section
common_rules:
    naming_conventions:
        - enforce: file_naming
          style: lowercase_with_underscores
        - enforce: constant_naming
          style: UPPERCASE_WITH_UNDERSCORES
    documentation:
        - enforce: changelog_updates
        - enforce: readme_maintenance
      

Code Style and Structure:

- Use semicolons at the end of statements
- Use single quotes for strings
- Use camelCase for variable and function names
- Organize code into folders by feature/domain
- Export modules instead of using default exports

Naming Conventions:

- Use descriptive names for variables and functions 
- Use camelCase for variables and functions
- Use PascalCase for class names
- Prefix global constants with GLOBAL_
- Suffix interfaces with Interface

TypeScript Usage:  

- Use TypeScript for type safety
- Add explicit types for function parameters and returns
- Use type aliases for complex types 
- Use interfaces for contracts between modules
- Use utility types like Partial and Required where applicable

Syntax and Formatting:

- Indent code with 2 spaces (no tabs)
- Open curly braces go on the same line
- Use single line formatting for simple code
- Add line breaks between logical sections
- Print width of 100 characters per line

UI and Styling:

- Use JSX for templating with React
- Keep component files colocated with CSS/SCSS
- Use BEM methodology for naming CSS classes
- Avoid using ids for styling
- Use CSS modules for component-scoped styling

Performance Optimization:

- Avoid unnecessary re-renders in React
- Use memoization for expensive functions 
- Lazy load routes and components
- Use Bun's build tooling for production optimizations

Key Conventions:

- Barrel index files to simplify imports
- Use environment variables for secrets
- Validate input data
- Handle errors gracefully
- Write tests for critical flows

Create a student information application. The app should have a register, a login and a
information landing activity. The following should be the functionalities of the app.

1. When you click on the register button, students should be redirected to the login.
2. When you click on the login button, students should be redirected to the landing activity.
3. Using intent, pass the data collected from the register activity to the login activity and
also from login activity to landing activity.