feat: Add toVercelAISDK method to support easy model creation #972
+299
−26
Conversation
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
fix!: VercelProvider now requires type safe parameters for Vercel models fix: Properly convert LD model parameters to Vercel model parameters
jsonbailey
force-pushed
the
jb/sdk-1532/support-tovercelaisdk-methods-in-provider
branch
from
b8e6700 to
9393389
Compare
jsonbailey
changed the base branch from
jb/sdk-1532/deprecate-tovercelaisdk
to
main
keelerm84
approved these changes
Oct 31, 2025
tanderson-ld
approved these changes
Oct 31, 2025
Contributor
|
@launchdarkly/browser size report |
Contributor
|
@launchdarkly/js-client-sdk size report |
Contributor
|
@launchdarkly/js-sdk-common size report |
Contributor
|
@launchdarkly/js-client-sdk-common size report |
jsonbailey
deleted the
jb/sdk-1532/support-tovercelaisdk-methods-in-provider
branch
Merged
jsonbailey
added a commit
that referenced
this pull request
Nov 5, 2025
🤖 I have created a release *beep* *boop* --- <details><summary>server-sdk-ai: 0.13.0</summary> ## [0.13.0](server-sdk-ai-v0.12.3...server-sdk-ai-v0.13.0) (2025-11-04) ### Features * Add support for trackStreamMetricsOf method ([#971](#971)) ([e18979e](e18979e)) ### Bug Fixes * Deprecated toVercelAISDK, trackVercelAISDKStreamTextMetrics, use `@launchdarkly/server-sdk-ai-vercel` package ([e18979e](e18979e)) </details> <details><summary>server-sdk-ai-langchain: 0.2.0</summary> ## [0.2.0](server-sdk-ai-langchain-v0.1.3...server-sdk-ai-langchain-v0.2.0) (2025-11-04) ### Features * Renamed createAIMetrics to getAIMetricsFromResponse ([#977](#977)) ([05b4667](05b4667)) ### Dependencies * The following workspace dependencies were updated * devDependencies * @launchdarkly/server-sdk-ai bumped from ^0.12.3 to ^0.13.0 </details> <details><summary>server-sdk-ai-openai: 0.2.0</summary> ## [0.2.0](server-sdk-ai-openai-v0.1.2...server-sdk-ai-openai-v0.2.0) (2025-11-04) ### Features * Renamed createAIMetrics to getAIMetricsFromResponse ([#977](#977)) ([05b4667](05b4667)) ### Dependencies * The following workspace dependencies were updated * devDependencies * @launchdarkly/server-sdk-ai bumped from ^0.12.3 to ^0.13.0 </details> <details><summary>server-sdk-ai-vercel: 0.2.0</summary> ## [0.2.0](server-sdk-ai-vercel-v0.1.2...server-sdk-ai-vercel-v0.2.0) (2025-11-04) ### ⚠ BREAKING CHANGES * VercelProvider now requires type safe parameters for Vercel models ### Features * Add support for tracking streaming text metics with ([28d3650](28d3650)) * Add toVercelAISDK method to support easy model creation ([#972](#972)) ([28d3650](28d3650)) * Renamed createAIMetrics to getAIMetricsFromResponse ([#977](#977)) ([05b4667](05b4667)) ### Bug Fixes * Check finishReason for an error when determining model success ([28d3650](28d3650)) * Prefer totalUsage over usage when mapping to LDTokenUsage ([28d3650](28d3650)) * Properly convert LD model parameters to Vercel model parameters ([28d3650](28d3650)) * VercelProvider now requires type safe parameters for Vercel models ([28d3650](28d3650)) ### Dependencies * The following workspace dependencies were updated * devDependencies * @launchdarkly/server-sdk-ai bumped from ^0.12.3 to ^0.13.0 </details> --- This PR was generated with [Release Please](https://github.com/googleapis/release-please). See [documentation](https://github.com/googleapis/release-please#release-please). <!-- CURSOR_SUMMARY --> --- > [!NOTE] > Release bumps: server AI SDK to 0.13.0 with stream metrics; LangChain/OpenAI/Vercel providers to 0.2.0 including metric API rename and Vercel type-safe params plus fixes. > > - **AI SDK (`packages/sdk/server-ai`) — 0.13.0** > - Feature: add `trackStreamMetricsOf`. > - Fix: deprecate `toVercelAISDK` and related helpers (moved to Vercel provider). > - **AI Providers — 0.2.0** > - `server-ai-langchain`/`server-ai-openai`: > - Rename `createAIMetrics` to `getAIMetricsFromResponse`. > - `server-ai-vercel`: > - Breaking: require type-safe params for Vercel models. > - Features: streaming text metrics tracking; `toVercelAISDK` helper. > - Fixes: check `finishReason` for errors; prefer `totalUsage`; correct LD→Vercel param mapping. > - **Examples/Manifest** > - Update versions to `@launchdarkly/[email protected]` and providers `@0.2.0` in examples and `.release-please-manifest.json`. > > <sup>Written by [Cursor Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit e2b5498. This will update automatically on new commits. Configure [here](https://cursor.com/dashboard?tab=bugbot).</sup> <!-- /CURSOR_SUMMARY --> --------- Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com> Co-authored-by: jsonbailey <[email protected]>
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.
feat: Add support for tracking streaming text metics with getAIMetricsFromStream
feat: Renamed createAIMetrics to getAIMetricsFromResponse (previous method is marked as deprecated)
fix!: VercelProvider now requires type safe parameters for Vercel models
fix: Properly convert LD model parameters to Vercel model parameters
fix: Prefer totalUsage over usage when mapping to LDTokenUsage
fix: Check finishReason for an error when determining model success
Note
Adds
toVercelAISDK, enforces typed Vercel model parameters with proper LD→Vercel mapping, and enhances usage/streaming metrics handling.toVercelAISDK()to build Vercel AI SDK config (mergesmessages, maps params).VercelAIModelParameters; update constructor andcreate()to usemapParameters().mapParameters()to convert LD params (e.g.,max_tokens,stop) to Vercel fields (maxTokens,stopSequences).mapUsageDataToLDTokenUsage(), supporttotalUsage/usage, incorporatefinishReason, and addcreateStreamMetrics()for streaming.types.tswithVercelAIModelParameters,VercelAISDKConfig,VercelAISDKMapOptions,VercelAISDKProviderand export them fromindex.ts.Written by Cursor Bugbot for commit 47a0875. This will update automatically on new commits. Configure here.