feat(router): same-model cross-provider fallback - #932
Open
stephenzwj wants to merge 1 commit into
Open
Conversation
When a client pins an explicit model and that model_id is also served by other enabled platforms, try those sibling rows immediately after the pinned one on fallback, ahead of the rest of the chain. Request-scoped so auto and sticky routing remain unchanged.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What it does
When a client pins an explicit model and that same
model_idis served by multiple enabled platforms, failed attempts now try sibling rows for the same model immediately after the pinned row, before falling through to unrelated models.Previously, a failed explicit pin could fall through to whichever unrelated model scored next in the chain.
Scope
preferredModelDbIdis set.Tests
Adds four regression tests covering:
Full server test suite: 214 files, 2,352 tests passed, 5 skipped.
Server build passes.