[Ask AI 02] refactor: upgrade Ask AI to AI SDK 7 - #229
Open
raviships wants to merge 1 commit into
Open
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
raviships
force-pushed
the
refactor/ask-ai-sdk-7
branch
from
August 22, 2026 03:59
8f01233 to
8387712
Compare
raviships
marked this pull request as ready for review
August 22, 2026 04:05
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Change
NodeSDKfrom Next.js instrumentation.observeandupdateActiveObservationlifecycle.AI SDK 7 replaces per-call experimental telemetry with registered integrations. Langfuse v5 replaces
updateActiveTracewith propagated attributes.Benchmark after the upgrade
The benchmark asked five documentation questions twice for each configuration. Quality is the percentage of question-specific checks passed. Cost uses estimated OpenAI token pricing.
provideLinkscallOn AI SDK 7, Luna with no reasoning matched GPT-4.1 mini's quality score. It cut estimated cost by 75% and median total time by 39%. The first event arrived 113 ms later.
Telemetry check
The live Gateway test emitted an
invoke_agentroot, astep 1child, and a model-call child. The Langfuse processor attached the trace name, session ID, tags, environment, token counts, model input, and model output. Its default filter kept all three spans.Checks
pnpm buildpasses.pnpm --filter docs exec tsc --noEmit --pretty falsepasses.