fix(provider): route Auto through native live catalogue pooling - #22
Merged
Conversation
The standalone router deployment is gone: model-router-ten.vercel.app answers DEPLOYMENT_NOT_FOUND, so every Auto request failed with an HTTP 404. Chutes resolves routing natively on the inference host now - the saved-pool alias \default\ - so Auto sends that alias to the same OpenAI-compatible host as concrete models, and steps down once to a compiled-in inline pool (Qwen/Qwen3.5-397B-A17B-TEE, zai-org/GLM-5.2-TEE) when the account has no routing pool saved at chutes.ai/app. The virtual picker id and every setting id stay as they were; only the routerEndpoint default moves (llm.chutes.ai/v1), since the old value pointed at a dead deployment.
A compiled-in pair of model ids goes stale the next time Chutes retires one. After the dashboard alias fails to resolve, list the current catalogue and retry with those chat-capable ids plus :latency so Chutes picks the fastest warm member and failovers to the next.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Auto was sending
model-routerto the retired Vercel deployment (DEPLOYMENT_NOT_FOUND). It now sends Chutes' nativedefaultalias tollm.chutes.aiand, if the account has no saved routing pool, retries once with a live inline pool built from the current catalogue (:latency).Test plan
npm run check(47/47 tests)chutes-model-provider-vscode-0.4.6.vsixand send a message with Auto (router)