Post: model fallback and routing without a provider SDK each (Neon AI Gateway #2)#1443
Open
bobbyonmagic wants to merge 3 commits into
Open
Post: model fallback and routing without a provider SDK each (Neon AI Gateway #2)#1443bobbyonmagic wants to merge 3 commits into
bobbyonmagic wants to merge 3 commits into
Conversation
Deploying devops-daily with
|
| Latest commit: |
3cd9fe1
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://f1a5198c.devops-daily.pages.dev |
| Branch Preview URL: | https://post-neon-model-fallback-and.devops-daily.pages.dev |
bobbyonmagic
force-pushed
the
post/neon-model-fallback-and-routing
branch
from
cb653bc to
3cd9fe1
Compare
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Second AI-gateway post (dated Jul 14). Through one OpenAI-compatible gateway, cross-provider fallback is a loop over model names instead of a stack of per-provider SDKs and error handlers.
Tested live: a request to ["not-a-real-model", "claude-haiku-4-5"] failed the first (400), fell back to Claude (200), and returned the answer plus a 'tried' record. Reuses neon-ai-gateway-demo. Extends fallback into a routing primitive (cost/latency/capability-first) and is honest about the caveats (log degradation, fall back to a comparable model).
Interactive: the fallback loop code, an animated terminal of the real failure/recovery, a tip callout, and a github card. OG generated, validated.