fix(audio): reject incompatible transform streams - #11565
Open
localai-org-maint-bot wants to merge 1 commit into
Open
fix(audio): reject incompatible transform streams#11565localai-org-maint-bot wants to merge 1 commit into
localai-org-maint-bot wants to merge 1 commit into
Conversation
The transform WebSocket accepted any model and opened its frame-based RPC. Any-to-any models use a different stream contract, so liquid-audio failed with an unimplemented RPC after the handshake. Reject incompatible model use cases before loading the backend. Direct realtime-audio callers to the OpenAI Realtime API. Assisted-by: Codex:gpt-5
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
The audio-transform WebSocket accepted
realtime_audiomodels and opened the frame-basedAudioTransformStreamRPC.liquid-audioimplements the separate any-to-anyAudioToAudioStreamcontract, so the request failed after the handshake withNotImplementedError.This PR validates the model use case before loading the backend. It directs any-to-any callers to the OpenAI Realtime API and documents the two streaming contracts.
Closes #11564
Verification
go test -tags="debug auth" ./core/http/endpoints/localai -ginkgo.focus="audio transform stream model validation|audio transform sample_rate bounds"go vet -tags="debug auth" ./core/http/endpoints/localaigit diff --checkThe full unfiltered endpoint suite currently has 30 unrelated testcontainer setup failures at
core/services/testutil/testdb.go:33; 228 specs pass.Notes for Reviewers
The fix keeps the valid
realtime_audiocapability onliquid-audio. It does not attempt to adapt a turn-based any-to-any model to the frame-synchronous transform protocol.Signed commits