Skip to content

Conversation

StudioPlatforms
Copy link

@StudioPlatforms StudioPlatforms commented Oct 16, 2025

Summary

This PR adds AI Stupid Level integration to Continue, providing 6 intelligent auto-routing models that automatically select the best AI model for each task.

Changes Made

1. core/llm/llms/AIStupidLevel.ts (New File)

  • Created new AI Stupid Level provider extending OpenAI base class
  • Configured with custom baseURL (https://aistupidlevel.info/v1/)
  • Set default model to auto-coding for optimal coding performance

2. core/llm/llms/index.ts

  • Added import for AIStupidLevel provider
  • Registered AIStupidLevel in LLMClasses array for provider discovery

Available Models

Users can configure any of these 6 auto-routing models:

  • auto - Best overall performance
  • auto-coding - Optimized for coding tasks (default)
  • auto-reasoning - Optimized for reasoning tasks
  • auto-creative - Optimized for creative tasks
  • auto-fastest - Optimized for speed
  • auto-cheapest - Optimized for cost efficiency

Benefits

  • Intelligent Routing: Automatically selects the best model based on task requirements
  • Multi-Provider Support: Leverages multiple AI providers (Anthropic, OpenAI, Google, etc.)
  • Cost Optimization: Choose between performance, speed, or cost
  • Easy Integration: Works seamlessly with existing Continue architecture

Configuration Example

{
  "models": [
    {
      "provider": "aistupidlevel",
      "model": "auto-coding",
      "apiKey": "your_api_key_here"
    }
  ]
}

Environment Variable

AI_STUPID_LEVEL_API_KEY=your_api_key_here

Users can obtain an API key from https://aistupidlevel.info


Summary by cubic

Adds Stupid Level provider that auto-routes to the best model per task. Registers it for discovery and sets auto-coding as the default.

  • New Features
    • Supports models: auto, auto-coding (default), auto-reasoning, auto-creative, auto-fastest, auto-cheapest.

@StudioPlatforms StudioPlatforms requested a review from a team as a code owner October 16, 2025 08:22
@StudioPlatforms StudioPlatforms requested review from tingwai and removed request for a team October 16, 2025 08:22
@dosubot dosubot bot added the size:S This PR changes 10-29 lines, ignoring generated files. label Oct 16, 2025
Copy link

github-actions bot commented Oct 16, 2025

All contributors have signed the CLA ✍️ ✅
Posted by the CLA Assistant Lite bot.

@StudioPlatforms
Copy link
Author

I have read the CLA Document and I hereby sign the CLA

@StudioPlatforms StudioPlatforms changed the title Add AI Stupid Level provider with 6 auto-routing models feat: add AI Stupid Level provider with 6 auto-routing models Oct 16, 2025
Copy link
Contributor

@cubic-dev-ai cubic-dev-ai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

No issues found across 2 files

@bdougie
Copy link
Collaborator

bdougie commented Oct 16, 2025

@StudioPlatforms thanks for opening this PR. Just want to point that we appreciate folks adding new providers, but it would also require a docs update as well. https://docs.continue.dev/customize/model-providers/overview

- Added comprehensive documentation for AIStupidLevel provider
- Documented intelligent routing strategies (auto-coding, auto-reasoning, etc.)
- Updated model providers overview to include AIStupidLevel
- Included configuration examples and key features
@dosubot dosubot bot added size:L This PR changes 100-499 lines, ignoring generated files. and removed size:S This PR changes 10-29 lines, ignoring generated files. labels Oct 17, 2025
@StudioPlatforms
Copy link
Author

@bdougie Thank you for the feedback! You're absolutely right - apologies for missing that initially. I've just pushed comprehensive documentation updates:

✅ Added detailed provider documentation at docs/customize/model-providers/more/aistupidlevel.mdx
✅ Updated the model providers overview to include AIStupidLevel in the Hosted Services section

The documentation includes:

  • Overview of what AIStupidLevel is (intelligent AI router with real-time benchmarks)
  • Configuration examples in both YAML and JSON formats
  • Detailed explanation of all 6 routing strategies (auto, auto-coding, auto-reasoning, auto-creative, auto-cheapest, auto-fastest)
  • How it works section with setup steps
  • Key features and benefits
  • Response headers information
  • Links to the website and community resources

Please let me know if there's anything else needed for the documentation or if you'd like any adjustments!

Copy link
Contributor

@cubic-dev-ai cubic-dev-ai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

No issues found across 2 files

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

size:L This PR changes 100-499 lines, ignoring generated files.

Projects

Status: Todo

Development

Successfully merging this pull request may close these issues.

2 participants