-
Notifications
You must be signed in to change notification settings - Fork 225
Upgrade Vercel SDK v4 -> v5 #1562
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
The reason for this is to try to use gpt-5 as a reasoning model so we can pass reasoing.effort: `minimal` when we need no-reasoning
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
No breaking changes that affect us?
@@ -355,9 +292,6 @@ export function useProviderEventHandler({ | |||
case 'reasoning': | |||
handleReasoning(data) | |||
break | |||
case 'redacted-reasoning': |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This has been removed from Vercel SDK. Here you can see the codemod to do the v4 -> v5 migration
https://github.com/vercel/ai/blob/main/packages/codemod/src/codemods/v5/replace-redacted-reasoning-type.ts#L67-L100
I fear a lot. This is ultra WIP |
Closing this one in favour of a more surgical approach #1565 |
What?
The reason for this is to try to use gpt-5 as a reasoning model so we can pass reasoing.effort:
minimal
when we need no-reasoningMigration guide
https://ai-sdk.dev/docs/migration-guides/migration-guide-5-0
TODO
gpt-4o
Telemetry
Now Vercel SDK output different names for things like usage. Now is
usage.inputTokens
andusage.outputTokens
. Review how this affects telemetry.