Adding MakeHub, the smart router for AI coding assistant #631
Conversation
|
There was a problem hiding this comment.
Pull Request Overview
This PR integrates MakeHub as a new AI provider into Kilocode to deliver consistent performance, reduced latency, and cost-effective access across various models. The changes include the addition of MakeHub-specific configuration options and UI components, updates to model fetching and API handling, and modifications to type definitions and provider schemas.
Reviewed Changes
Copilot reviewed 40 out of 40 changed files in this pull request and generated 1 comment.
Show a summary per file
| File | Description |
|---|---|
| webview-ui/src/components/ui/hooks/useSelectedModel.ts | Added support for MakeHub in model selection logic. |
| webview-ui/src/components/settings/providers/MakeHub.tsx | Introduced a new settings component for configuring MakeHub. |
| webview-ui/src/components/settings/ApiOptions.tsx | Included MakeHub in provider switch-case and configuration defaults. |
| src/shared/api.ts, ProfileValidator.ts, and others | Updated provider lists and type definitions to include MakeHub. |
| src/api/providers/makehub.ts | New API handler for MakeHub with cost calculation and message streaming. |
| src/api/providers/fetchers/makehub.ts | New model fetcher for MakeHub integrating API response parsing. |
| packages/types and evals packages | Updated type definitions and provider schemas for MakeHub. |
Comments suppressed due to low confidence (1)
src/api/providers/makehub.ts:1
- The import of 'Anthropic' is unused in this file. Removing it may improve code clarity.
import { Anthropic } from "@anthropic-ai/sdk"
|
Hello, I’ve implemented the needed corrections and pushed the updates. Best, |
|
Hi, I have added Makehub to the necessary test files. Best |
|
Hello, I have update the PR to the lastest commits. Best, |
Context
As daily users of Kilocode, my team and I frequently encounter rate limits and performance inconsistencies when using certain AI providers. These limitations hinder our development workflow, especially when leveraging advanced models. We seek a solution that offers:
-consistent performance
-reduced latency
-cost-effective access to various AI models
-A Solution for Developers by Developers.
So, We propose integrating MakeHub.ai as an AI provider within Kilocode. MakeHub.ai offers a high-speed LLM API that performs real-time speed and price arbitrage across multiple providers for close and open source models. Users can define performance parameters such as speed and price, allowing MakeHub to select the most cost-effective provider that meets these requirements. This integration would enable developers to experience consistent performance and pricing across various models, all through a single API key.
Implementation
Some description of HOW you achieved it. Perhaps give a high level description of the program flow. Did you need to refactor something? What tradeoffs did you take? Are there things in here which you’d particularly like people to pay close attention to?
We’ve followed Kilocode’s current pattern for adding providers. Since MakeHub is OpenAI API compatible (including chat/completions/embeddings endpoints), integration required no major refactor. Also, we add MakeHub in the necessary tests.
Screenshots
How to Test
A straightforward scenario of how to test your changes will help reviewers that are not familiar with the part of the code that you are changing but want to see it in action. This section can include a description or step-by-step instructions of how to get to the state of v2 that your change affects.
Get in Touch
We'd love to have a way to chat with you about your changes if necessary. If you're in the Kilo Code Discord, please share your handle here. -->
We’d love to discuss this integration further and hear your feedback.
We’re on the Kilocode Discord: