Skip to content

Conversation

@carlesandres
Copy link

@carlesandres carlesandres commented Jan 29, 2026

Description

This extension provides quick access to search, browse, compare, and explore AI model specifications, pricing, and capabilities from the models.dev database.

Screencast

Recording

Checklist

- Fix linting
- docs: remove stale-while-revalidate mention
- feat: add disk cache for instant model data loading
- Add metadata images
- docs: rewrite README with clearer command descriptions
- style(compare): use Raycast Color constant for green
- style(compare): use Switch icon for compare action
- refactor: consolidate model actions into single component
- chore: update branding and dependencies
- style: fix formatting and trailing commas
- chore: reorder commands in package.json
- fix(compare): enable text search filtering
- feat(compare): reduce max models to 3
- feat(compare): allow removing models from dropdown
- refactor: improve list views with accurate counts and search
- feat: add model count and over 5 filter
- feat: expand pricing filter options
- feat: add non-free filter and remove price grouping
- feat: base pricing explorer on output tokens
- refactor: simplify pricing explorer list accessories
- fix: render markdown tables with proper borders
- style: align prices with fixed-width formatting
- feat: show input and output pricing in model list
- refactor: extract capability accessories into shared utility
- style: format modalities as bullet list
- chore: update keywords
- fix: render markdown tables with contiguous rows
- chore: update extension icon
- docs: expand changelog with detailed feature list
- chore: remove bun.lock in favor of npm
- chore: add keywords and package-lock for store publication
- Delete PRD
- feat: implement models.dev Raycast extension
- Initial commit: models.dev Raycast extension scaffold
@raycastbot
Copy link
Collaborator

Congratulations on your new Raycast extension! 🚀

We're currently experiencing a high volume of incoming requests. As a result, the initial review may take up to 10-15 business days.

Once the PR is approved and merged, the extension will be available on our Store.

@carlesandres carlesandres marked this pull request as ready for review January 29, 2026 22:43
@greptile-apps
Copy link
Contributor

greptile-apps bot commented Jan 29, 2026

Greptile Overview

Greptile Summary

This PR adds a new extension that provides quick access to AI model information from models.dev, including search, browsing, comparison, and pricing exploration capabilities.

Key Changes:

  • Adds 5 commands: Search Models, Browse Providers, Find by Capability, Compare Models, and Pricing Explorer
  • Implements stale-while-revalidate caching for optimal performance
  • Includes comprehensive filtering, sorting, and comparison features
  • Follows Raycast standards for Prettier, ESLint configuration, and CHANGELOG formatting

Issues Found:

  • Inconsistent messaging about maximum model count in compare-models.tsx (code enforces 3, message says "2-4")

Confidence Score: 4.5/5

  • Safe to merge after fixing the model count messaging inconsistency in compare-models.tsx
  • High-quality implementation with proper architecture, caching, and Raycast standards compliance. Only minor messaging inconsistency found.
  • extensions/models-dev/src/compare-models.tsx needs the max model count message corrected

Important Files Changed

Filename Overview
extensions/models-dev/package.json Properly configured extension manifest with all required fields and correct Prettier/ESLint setup
extensions/models-dev/src/lib/api.ts Clean API layer with proper caching, data transformation, and fallback handling
extensions/models-dev/src/hooks/useModelsData.ts Well-implemented hook with stale-while-revalidate caching pattern for optimal UX
extensions/models-dev/src/compare-models.tsx Model comparison with inconsistent messaging about max models (code enforces 3, message says 2-4)

Copy link
Contributor

@greptile-apps greptile-apps bot left a comment

Choose a reason for hiding this comment

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

4 files reviewed, 1 comment

Edit Code Review Agent Settings | Greptile

showToast({
style: Toast.Style.Failure,
title: "Select at least 2 models",
message: "Choose 2-4 models to compare",
Copy link
Contributor

Choose a reason for hiding this comment

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

Inconsistent max model count messaging. The code enforces max 3 models (line 84), but this message says "2-4 models"

Suggested change
message: "Choose 2-4 models to compare",
message: "Choose 2-3 models to compare",

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

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants