feat(service-ai): per-instance gatewayModel option#1647
Merged
Conversation
…WAY_MODEL) AIServicePluginOptions gains `gatewayModel?: string`. detectAdapter() uses `this.options.gatewayModel ?? process.env.AI_GATEWAY_MODEL`, so a multi-tenant host can route the gateway model per kernel (e.g. by plan) instead of relying on the single process-wide env var. Omitted → unchanged env-based behavior. Tests: option wins over env; falls back to env when option absent. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
AIServicePluginOptionsgains an optionalgatewayModel?: string.detectAdapter()now uses:So a host can select the Vercel AI Gateway model per plugin instance instead of only via the process-wide
AI_GATEWAY_MODELenv var.Why
A multi-tenant runtime builds one
AIServicePluginper environment kernel and needs to route the model per tenant/plan (e.g. free → haiku, paid → sonnet) within a single process. The env var is process-global and can't express that. Omitting the option preserves the exact current behavior (env fallback).This is the open-core mechanism; the routing policy stays in the (closed) cloud runtime (cloud ADR-0005).
Tests
AI_GATEWAY_MODELai-service.test.tssuite: 95 passed🤖 Generated with Claude Code