Skip to content

feat: dynamic AI model registry fetched from provider APIs#250

Open
WardaBibi wants to merge 2 commits intoxataio:mainfrom
WardaBibi:feat/dynamic-model-registry
Open

feat: dynamic AI model registry fetched from provider APIs#250
WardaBibi wants to merge 2 commits intoxataio:mainfrom
WardaBibi:feat/dynamic-model-registry

Conversation

@WardaBibi
Copy link
Copy Markdown

Summary

  • Replace hardcoded model lists with live fetches from OpenAI, Anthropic, Google, and DeepSeek APIs at startup
  • Providers load in parallel via Promise.allSettled — one failure does not block others
  • Aliases (chat/title/summary) resolved dynamically using a small-model heuristic (mini, flash, haiku, lite, nano)
  • Fix React hydration warning on <body> and update next-env.d.ts reference syntax

Test plan

  • Start dev server and confirm no [builtin] warnings in terminal
  • Verify model dropdown in UI shows live models from configured providers
  • Remove one API key temporarily and confirm app still loads with remaining providers

Replace hardcoded model lists with live fetches from OpenAI, Anthropic,
Google, and DeepSeek APIs at startup. Providers load in parallel via
Promise.allSettled so one failure does not block the others. Aliases
(chat/title/summary) are resolved dynamically using a small-model
heuristic. Also fix React hydration warning on <body> and update
next-env.d.ts reference syntax.
@WardaBibi
Copy link
Copy Markdown
Author

Hi team! Can you please approve the workflow so the CI checks can run? Thanks!

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

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant