Files
LocalAI/pkg/grpc/embed.go
Richard Palethorpe 5d0c43ec6e feat(realtime): Semantic VAD EOU token (#10444)
* feat(realtime): EOU-driven semantic_vad turn detection

Add a `semantic_vad` turn-detection mode to the realtime API that feeds
the transcription model live and decides "the user finished speaking"
from the `<EOU>` end-of-utterance token rather than from silence alone.
When EOU fires the turn commits immediately (~0.3s); otherwise it falls
back to an eagerness-scaled silence threshold (low/med/high = 8/4/2s).

Plumbing, bottom to top:

- proto: `AudioTranscriptionLive` bidirectional RPC (config-first oneof,
  mono float PCM @16k, ready-ack / Unimplemented degrade signal) plus
  `TranscriptResult.eou` for the unary retranscribe gate.
- pkg/grpc: client/server/base/embed scaffolding for the bidi stream,
  modeled on AudioTransformStream; release stream conns on terminal Recv.
- parakeet-cpp: live transcription RPC with per-C-call engine locking
  (one live stream per turn, finalize+free at commit); bump parakeet.cpp
  to ABI v5 — incremental StreamingMel (no more quadratic per-feed mel
  recompute that delayed EOU on long turns) and the <EOU>/<EOB> split;
  strip the literal <EOU>/<EOB> from offline text and set Eou.
- core/backend: LiveTranscriptionSession wrapper + pipeline
  `turn_detection:` config block (type/eagerness/retranscribe).
- realtime: semantic_vad integration — live input captions streamed as
  transcription deltas while the user speaks, EOU-immediate commit with
  eagerness fallback, optional retranscribe gate (batch re-decode must
  also end in <EOU> to confirm), clause synthesis off the LLM token
  callback, and per-turn live-transcription / model_load telemetry.
- UI: show the realtime pipeline components as a vertical list.

Docs and tests included; opt-in via the pipeline YAML or per-session
`session.update`. Non-streaming STT backends degrade to silence-only.

Assisted-by: Claude Code:claude-opus-4-8 [Read] [Edit] [Write] [Bash]
Assisted-by: Claude Code:claude-fable-5 [Read] [Edit] [Bash]
Signed-off-by: Richard Palethorpe <io@richiejp.com>

* feat(realtime): explicit formally-verified state machines + parakeet streaming driver

The realtime API had several implicit state machines whose state was inferred
from scattered booleans, channels, and five separate mutexes, leaving
illegal/inconsistent states reachable. Make them explicit and keep the
implementation in step with a formal design; rework the parakeet streaming
backend along the same lines.

Realtime state machines (M1-M5). Each is a sealed sum-type State/Event/Effect
with a total, pure Next(state,event)->(state,[]effect) behind a single-writer
Coordinator:

  M1 conncoord    connection lifecycle: VAD toggle + once-only teardown
                  (replaces vadServerStarted + a `done` channel closed from
                  two sites).
  M2 turncoord    turn detection: collapses speechStarted and the live-stream
                  "turn open" flag into one state, so discardTurn can no longer
                  desync them and suppress the next onset.
  M3 respcoord    response coordination: serializes the dual-writer
                  start/cancel so at most one response is live; one
                  response.done per response.create.
  M4 compactcoord conversation compaction: single-flight (replaces the
                  `compacting atomic.Bool` CAS).
  M5 ttscoord     TTS pipeline: open->closing->closed, idempotent wait(),
                  rejects enqueue-after-close (was a silent drop).

The Coordinator/Sink/Next plumbing — only the sealed types and Next differed
per machine — is extracted once into core/http/endpoints/openai/coordinator as
a generic Coordinator[S,E,F]; each machine keeps its public API via type
aliases, so no sink, call-site, or test moved.

Hierarchy. session_lifecycle.fizz models M1 as the parent region with its
children (M2/M3/M4) as one statechart and asserts ChildrenDieWithParent (conn
torn => all children terminal, none start after teardown). respcoord and
compactcoord gain an absorbing Terminated state + Shutdown event; conncoord's
teardown drives the children terminal. This closes a compaction teardown gap: a
fire-and-forget compaction could outlive a torn session — compactionSink now
takes a session-scoped cancellable context + WaitGroup and joins the in-flight
summarize+evict on shutdown.

Formal verification. formal-verification/ holds one authoritative FizzBee spec
per machine plus the composition spec, each with an always-assertion and a
documented one-line edit that makes the checker fail (verified non-vacuous).
scripts/realtime-conformance.sh is fail-closed: all Go conformance suites under
-race AND a model-check of every .fizz spec; a missing FizzBee is a hard error
(only the loud REALTIME_CONFORMANCE_SKIP_FIZZBEE=1 bypasses it, never in CI).
FizzBee is pinned by sha256 and installed via scripts/install-fizzbee.sh into
.tools/ (gitignored). Wired as make test-realtime-conformance, a CI workflow,
and a pre-commit path filter. Go conformance tests are Ginkgo/Gomega (per the
repo's forbidigo lint): transition tables + fixed-seed property walks +
concurrent/-race specs, no rapid dependency. Design map:
docs/design/realtime-state-machines.md.

Parakeet streaming backend. The same treatment applied to the parakeet-cpp
streaming paths:
- AudioTranscriptionStream returns codes.Unimplemented for non-streaming models
  instead of decoding offline and emitting it as one delta + final. A client
  that asked for streaming learns the model cannot stream rather than receiving
  a batch result shaped like a stream. New grpcerrors.StreamTranscriptionUnsupported
  carries that signal; the HTTP /v1/audio/transcriptions stream path surfaces it
  as an SSE error event. Mirrors AudioTranscriptionLive, which already did this.
- utteranceBoundary (boundary.go): a single definition of the end-of-utterance
  latch, replacing three open-coded finalEou toggles. Modelled as a two-valued
  type so illegal states are unrepresentable.
- Shared decode driver (driver.go): streamFeedResult (one per-feed event) +
  feedChunk (hides the ABI v4 JSON vs text-only split) + feedSlices + flushTail.
  The feed loop is written once.
- AudioTranscriptionLive becomes a bidi adapter: it streams the per-feed
  {delta,eou,eob,words} the realtime turn detector consumes and a terminal
  FinalResult carrying only Text. Segments/duration/eou are offline-only and no
  longer produced (nor read) on the live path; liveTraceState drops the terminal
  eou and keeps the per-feed eou_events count.
- AudioTranscriptionStream + streamJSON merge into one driver-based function;
  streamSegmenter is generalized to the unified event with a text-only fallback
  that preserves the legacy (no-words) library's per-utterance segmentation.

Verified: build/vet/gofumpt clean, golangci-lint 0 issues, all coordinator and
parakeet packages under -race, the fail-closed conformance gate green, and
make test-realtime (12 e2e WS+WebRTC).

Assisted-by: Claude:claude-opus-4-8 [Claude Code]
Signed-off-by: Richard Palethorpe <io@richiejp.com>

---------

Signed-off-by: Richard Palethorpe <io@richiejp.com>
2026-06-30 09:01:22 +02:00

859 lines
25 KiB
Go

package grpc
import (
"context"
"io"
"sync"
pb "github.com/mudler/LocalAI/pkg/grpc/proto"
"google.golang.org/grpc"
"google.golang.org/grpc/metadata"
)
var _ Backend = new(embedBackend)
var _ pb.Backend_PredictStreamServer = new(embedBackendServerStream)
type embedBackend struct {
s *server
}
func (e *embedBackend) IsBusy() bool {
return e.s.llm.Busy()
}
func (e *embedBackend) HealthCheck(ctx context.Context) (bool, error) {
return true, nil
}
func (e *embedBackend) Embeddings(ctx context.Context, in *pb.PredictOptions, opts ...grpc.CallOption) (*pb.EmbeddingResult, error) {
return e.s.Embedding(ctx, in)
}
func (e *embedBackend) Predict(ctx context.Context, in *pb.PredictOptions, opts ...grpc.CallOption) (*pb.Reply, error) {
return e.s.Predict(ctx, in)
}
func (e *embedBackend) LoadModel(ctx context.Context, in *pb.ModelOptions, opts ...grpc.CallOption) (*pb.Result, error) {
return e.s.LoadModel(ctx, in)
}
func (e *embedBackend) PredictStream(ctx context.Context, in *pb.PredictOptions, f func(reply *pb.Reply), opts ...grpc.CallOption) error {
bs := &embedBackendServerStream{
ctx: ctx,
fn: f,
}
return e.s.PredictStream(in, bs)
}
func (e *embedBackend) GenerateImage(ctx context.Context, in *pb.GenerateImageRequest, opts ...grpc.CallOption) (*pb.Result, error) {
return e.s.GenerateImage(ctx, in)
}
func (e *embedBackend) GenerateVideo(ctx context.Context, in *pb.GenerateVideoRequest, opts ...grpc.CallOption) (*pb.Result, error) {
return e.s.GenerateVideo(ctx, in)
}
func (e *embedBackend) TTS(ctx context.Context, in *pb.TTSRequest, opts ...grpc.CallOption) (*pb.Result, error) {
return e.s.TTS(ctx, in)
}
func (e *embedBackend) TTSStream(ctx context.Context, in *pb.TTSRequest, f func(reply *pb.Reply), opts ...grpc.CallOption) error {
bs := &embedBackendServerStream{
ctx: ctx,
fn: f,
}
return e.s.TTSStream(in, bs)
}
func (e *embedBackend) SoundGeneration(ctx context.Context, in *pb.SoundGenerationRequest, opts ...grpc.CallOption) (*pb.Result, error) {
return e.s.SoundGeneration(ctx, in)
}
func (e *embedBackend) Detect(ctx context.Context, in *pb.DetectOptions, opts ...grpc.CallOption) (*pb.DetectResponse, error) {
return e.s.Detect(ctx, in)
}
func (e *embedBackend) Depth(ctx context.Context, in *pb.DepthRequest, opts ...grpc.CallOption) (*pb.DepthResponse, error) {
return e.s.Depth(ctx, in)
}
func (e *embedBackend) FaceVerify(ctx context.Context, in *pb.FaceVerifyRequest, opts ...grpc.CallOption) (*pb.FaceVerifyResponse, error) {
return e.s.FaceVerify(ctx, in)
}
func (e *embedBackend) FaceAnalyze(ctx context.Context, in *pb.FaceAnalyzeRequest, opts ...grpc.CallOption) (*pb.FaceAnalyzeResponse, error) {
return e.s.FaceAnalyze(ctx, in)
}
func (e *embedBackend) VoiceVerify(ctx context.Context, in *pb.VoiceVerifyRequest, opts ...grpc.CallOption) (*pb.VoiceVerifyResponse, error) {
return e.s.VoiceVerify(ctx, in)
}
func (e *embedBackend) VoiceAnalyze(ctx context.Context, in *pb.VoiceAnalyzeRequest, opts ...grpc.CallOption) (*pb.VoiceAnalyzeResponse, error) {
return e.s.VoiceAnalyze(ctx, in)
}
func (e *embedBackend) VoiceEmbed(ctx context.Context, in *pb.VoiceEmbedRequest, opts ...grpc.CallOption) (*pb.VoiceEmbedResponse, error) {
return e.s.VoiceEmbed(ctx, in)
}
func (e *embedBackend) AudioTranscription(ctx context.Context, in *pb.TranscriptRequest, opts ...grpc.CallOption) (*pb.TranscriptResult, error) {
return e.s.AudioTranscription(ctx, in)
}
func (e *embedBackend) AudioTranscriptionStream(ctx context.Context, in *pb.TranscriptRequest, f func(chunk *pb.TranscriptStreamResponse), opts ...grpc.CallOption) error {
bs := &embedBackendAudioTranscriptionStream{
ctx: ctx,
fn: f,
}
return e.s.AudioTranscriptionStream(in, bs)
}
func (e *embedBackend) TokenizeString(ctx context.Context, in *pb.PredictOptions, opts ...grpc.CallOption) (*pb.TokenizationResponse, error) {
return e.s.TokenizeString(ctx, in)
}
func (e *embedBackend) Status(ctx context.Context) (*pb.StatusResponse, error) {
return e.s.Status(ctx, &pb.HealthMessage{})
}
func (e *embedBackend) StoresSet(ctx context.Context, in *pb.StoresSetOptions, opts ...grpc.CallOption) (*pb.Result, error) {
return e.s.StoresSet(ctx, in)
}
func (e *embedBackend) StoresDelete(ctx context.Context, in *pb.StoresDeleteOptions, opts ...grpc.CallOption) (*pb.Result, error) {
return e.s.StoresDelete(ctx, in)
}
func (e *embedBackend) StoresGet(ctx context.Context, in *pb.StoresGetOptions, opts ...grpc.CallOption) (*pb.StoresGetResult, error) {
return e.s.StoresGet(ctx, in)
}
func (e *embedBackend) StoresFind(ctx context.Context, in *pb.StoresFindOptions, opts ...grpc.CallOption) (*pb.StoresFindResult, error) {
return e.s.StoresFind(ctx, in)
}
func (e *embedBackend) Rerank(ctx context.Context, in *pb.RerankRequest, opts ...grpc.CallOption) (*pb.RerankResult, error) {
return e.s.Rerank(ctx, in)
}
func (e *embedBackend) TokenClassify(ctx context.Context, in *pb.TokenClassifyRequest, opts ...grpc.CallOption) (*pb.TokenClassifyResponse, error) {
return e.s.TokenClassify(ctx, in)
}
func (e *embedBackend) Score(ctx context.Context, in *pb.ScoreRequest, opts ...grpc.CallOption) (*pb.ScoreResponse, error) {
return e.s.Score(ctx, in)
}
func (e *embedBackend) VAD(ctx context.Context, in *pb.VADRequest, opts ...grpc.CallOption) (*pb.VADResponse, error) {
return e.s.VAD(ctx, in)
}
func (e *embedBackend) Diarize(ctx context.Context, in *pb.DiarizeRequest, opts ...grpc.CallOption) (*pb.DiarizeResponse, error) {
return e.s.Diarize(ctx, in)
}
func (e *embedBackend) SoundDetection(ctx context.Context, in *pb.SoundDetectionRequest, opts ...grpc.CallOption) (*pb.SoundDetectionResponse, error) {
return e.s.SoundDetection(ctx, in)
}
func (e *embedBackend) AudioEncode(ctx context.Context, in *pb.AudioEncodeRequest, opts ...grpc.CallOption) (*pb.AudioEncodeResult, error) {
return e.s.AudioEncode(ctx, in)
}
func (e *embedBackend) AudioDecode(ctx context.Context, in *pb.AudioDecodeRequest, opts ...grpc.CallOption) (*pb.AudioDecodeResult, error) {
return e.s.AudioDecode(ctx, in)
}
func (e *embedBackend) AudioTransform(ctx context.Context, in *pb.AudioTransformRequest, opts ...grpc.CallOption) (*pb.AudioTransformResult, error) {
return e.s.AudioTransform(ctx, in)
}
func (e *embedBackend) AudioTransformStream(ctx context.Context, opts ...grpc.CallOption) (AudioTransformStreamClient, error) {
// In-process bidi stream is two channels paired with two facades:
// the server side reads requests / writes responses; the client side
// is its mirror.
reqs := make(chan *pb.AudioTransformFrameRequest, 4)
resps := make(chan *pb.AudioTransformFrameResponse, 4)
srvDone := make(chan error, 1)
server := &embedBackendAudioTransformStream{
ctx: ctx,
reqs: reqs,
resps: resps,
}
go func() {
err := e.s.AudioTransformStream(server)
// Backend has finished — no more responses will arrive.
close(resps)
srvDone <- err
}()
return &embedBackendAudioTransformStreamClient{
ctx: ctx,
reqs: reqs,
resps: resps,
srvDone: srvDone,
}, nil
}
func (e *embedBackend) AudioTranscriptionLive(ctx context.Context, opts ...grpc.CallOption) (AudioTranscriptionLiveClient, error) {
reqs := make(chan *pb.TranscriptLiveRequest, 4)
resps := make(chan *pb.TranscriptLiveResponse, 4)
srvDone := make(chan error, 1)
server := &embedBackendAudioTranscriptionLiveStream{
ctx: ctx,
reqs: reqs,
resps: resps,
}
go func() {
err := e.s.AudioTranscriptionLive(server)
// Stash the terminal error BEFORE closing resps: a caller blocked in
// Recv wakes on the close and must find the error (the ready-ack
// contract surfaces Unimplemented through that first Recv).
srvDone <- err
close(resps)
}()
return &embedBackendAudioTranscriptionLiveStreamClient{
ctx: ctx,
reqs: reqs,
resps: resps,
srvDone: srvDone,
}, nil
}
func (e *embedBackend) Forward(ctx context.Context, opts ...grpc.CallOption) (ForwardClient, error) {
reqs := make(chan *pb.ForwardRequest, 8)
resps := make(chan *pb.ForwardReply, 8)
srvDone := make(chan error, 1)
server := &embedBackendForwardStream{ctx: ctx, reqs: reqs, resps: resps}
go func() {
err := e.s.Forward(server)
close(resps)
srvDone <- err
}()
return &embedBackendForwardStreamClient{
ctx: ctx,
reqs: reqs,
resps: resps,
srvDone: srvDone,
}, nil
}
func (e *embedBackend) AudioToAudioStream(ctx context.Context, opts ...grpc.CallOption) (AudioToAudioStreamClient, error) {
reqs := make(chan *pb.AudioToAudioRequest, 8)
resps := make(chan *pb.AudioToAudioResponse, 8)
srvDone := make(chan error, 1)
server := &embedBackendAudioToAudioStream{
ctx: ctx,
reqs: reqs,
resps: resps,
}
go func() {
err := e.s.AudioToAudioStream(server)
close(resps)
srvDone <- err
}()
return &embedBackendAudioToAudioStreamClient{
ctx: ctx,
reqs: reqs,
resps: resps,
srvDone: srvDone,
}, nil
}
func (e *embedBackend) ModelMetadata(ctx context.Context, in *pb.ModelOptions, opts ...grpc.CallOption) (*pb.ModelMetadataResponse, error) {
return e.s.ModelMetadata(ctx, in)
}
func (e *embedBackend) GetTokenMetrics(ctx context.Context, in *pb.MetricsRequest, opts ...grpc.CallOption) (*pb.MetricsResponse, error) {
return e.s.GetMetrics(ctx, in)
}
func (e *embedBackend) StartFineTune(ctx context.Context, in *pb.FineTuneRequest, opts ...grpc.CallOption) (*pb.FineTuneJobResult, error) {
return e.s.StartFineTune(ctx, in)
}
func (e *embedBackend) FineTuneProgress(ctx context.Context, in *pb.FineTuneProgressRequest, f func(update *pb.FineTuneProgressUpdate), opts ...grpc.CallOption) error {
bs := &embedBackendFineTuneProgressStream{
ctx: ctx,
fn: f,
}
return e.s.FineTuneProgress(in, bs)
}
func (e *embedBackend) StopFineTune(ctx context.Context, in *pb.FineTuneStopRequest, opts ...grpc.CallOption) (*pb.Result, error) {
return e.s.StopFineTune(ctx, in)
}
func (e *embedBackend) ListCheckpoints(ctx context.Context, in *pb.ListCheckpointsRequest, opts ...grpc.CallOption) (*pb.ListCheckpointsResponse, error) {
return e.s.ListCheckpoints(ctx, in)
}
func (e *embedBackend) ExportModel(ctx context.Context, in *pb.ExportModelRequest, opts ...grpc.CallOption) (*pb.Result, error) {
return e.s.ExportModel(ctx, in)
}
func (e *embedBackend) StartQuantization(ctx context.Context, in *pb.QuantizationRequest, opts ...grpc.CallOption) (*pb.QuantizationJobResult, error) {
return e.s.StartQuantization(ctx, in)
}
func (e *embedBackend) QuantizationProgress(ctx context.Context, in *pb.QuantizationProgressRequest, f func(update *pb.QuantizationProgressUpdate), opts ...grpc.CallOption) error {
bs := &embedBackendQuantizationProgressStream{
ctx: ctx,
fn: f,
}
return e.s.QuantizationProgress(in, bs)
}
func (e *embedBackend) StopQuantization(ctx context.Context, in *pb.QuantizationStopRequest, opts ...grpc.CallOption) (*pb.Result, error) {
return e.s.StopQuantization(ctx, in)
}
func (e *embedBackend) Free(ctx context.Context) error {
_, err := e.s.Free(ctx, &pb.HealthMessage{})
return err
}
var _ pb.Backend_AudioTransformStreamServer = new(embedBackendAudioTransformStream)
var _ AudioTransformStreamClient = new(embedBackendAudioTransformStreamClient)
var _ pb.Backend_AudioToAudioStreamServer = new(embedBackendAudioToAudioStream)
var _ AudioToAudioStreamClient = new(embedBackendAudioToAudioStreamClient)
var _ pb.Backend_AudioTranscriptionLiveServer = new(embedBackendAudioTranscriptionLiveStream)
var _ AudioTranscriptionLiveClient = new(embedBackendAudioTranscriptionLiveStreamClient)
// embedBackendAudioTransformStream is the server side of an in-process bidi
// stream. The hosted server reads requests from `reqs` (closed by client when
// done sending) and writes responses to `resps`.
type embedBackendAudioTransformStream struct {
ctx context.Context
reqs <-chan *pb.AudioTransformFrameRequest
resps chan<- *pb.AudioTransformFrameResponse
}
func (e *embedBackendAudioTransformStream) Send(resp *pb.AudioTransformFrameResponse) error {
select {
case e.resps <- resp:
return nil
case <-e.ctx.Done():
return e.ctx.Err()
}
}
func (e *embedBackendAudioTransformStream) Recv() (*pb.AudioTransformFrameRequest, error) {
select {
case req, ok := <-e.reqs:
if !ok {
return nil, io.EOF
}
return req, nil
case <-e.ctx.Done():
return nil, e.ctx.Err()
}
}
func (e *embedBackendAudioTransformStream) SetHeader(md metadata.MD) error { return nil }
func (e *embedBackendAudioTransformStream) SendHeader(md metadata.MD) error { return nil }
func (e *embedBackendAudioTransformStream) SetTrailer(md metadata.MD) {}
func (e *embedBackendAudioTransformStream) Context() context.Context { return e.ctx }
func (e *embedBackendAudioTransformStream) SendMsg(m any) error {
if x, ok := m.(*pb.AudioTransformFrameResponse); ok {
return e.Send(x)
}
return nil
}
func (e *embedBackendAudioTransformStream) RecvMsg(m any) error {
// gRPC bidi streaming uses Recv() directly; RecvMsg is unused on this path.
return nil
}
// embedBackendAudioTransformStreamClient is the caller-facing side. It
// mirrors the server-side stream over the same channels.
type embedBackendAudioTransformStreamClient struct {
ctx context.Context
reqs chan<- *pb.AudioTransformFrameRequest
resps <-chan *pb.AudioTransformFrameResponse
srvDone <-chan error
closeOnce bool
}
func (e *embedBackendAudioTransformStreamClient) Send(req *pb.AudioTransformFrameRequest) error {
select {
case e.reqs <- req:
return nil
case <-e.ctx.Done():
return e.ctx.Err()
}
}
func (e *embedBackendAudioTransformStreamClient) Recv() (*pb.AudioTransformFrameResponse, error) {
select {
case resp, ok := <-e.resps:
if !ok {
// Server-side finished. Surface its terminal error if any.
select {
case err := <-e.srvDone:
if err != nil {
return nil, err
}
default:
}
return nil, io.EOF
}
return resp, nil
case <-e.ctx.Done():
return nil, e.ctx.Err()
}
}
func (e *embedBackendAudioTransformStreamClient) CloseSend() error {
if e.closeOnce {
return nil
}
e.closeOnce = true
close(e.reqs)
return nil
}
func (e *embedBackendAudioTransformStreamClient) Context() context.Context { return e.ctx }
// embedBackendAudioTranscriptionLiveStream is the in-process server-side
// handle for the bidirectional live ASR RPC. Mirrors
// embedBackendAudioTransformStream — the hosted server reads requests from
// `reqs` (closed by client when done sending) and writes responses to `resps`.
type embedBackendAudioTranscriptionLiveStream struct {
ctx context.Context
reqs <-chan *pb.TranscriptLiveRequest
resps chan<- *pb.TranscriptLiveResponse
}
func (e *embedBackendAudioTranscriptionLiveStream) Send(resp *pb.TranscriptLiveResponse) error {
select {
case e.resps <- resp:
return nil
case <-e.ctx.Done():
return e.ctx.Err()
}
}
func (e *embedBackendAudioTranscriptionLiveStream) Recv() (*pb.TranscriptLiveRequest, error) {
select {
case req, ok := <-e.reqs:
if !ok {
return nil, io.EOF
}
return req, nil
case <-e.ctx.Done():
return nil, e.ctx.Err()
}
}
func (e *embedBackendAudioTranscriptionLiveStream) SetHeader(md metadata.MD) error { return nil }
func (e *embedBackendAudioTranscriptionLiveStream) SendHeader(md metadata.MD) error { return nil }
func (e *embedBackendAudioTranscriptionLiveStream) SetTrailer(md metadata.MD) {}
func (e *embedBackendAudioTranscriptionLiveStream) Context() context.Context { return e.ctx }
func (e *embedBackendAudioTranscriptionLiveStream) SendMsg(m any) error {
if x, ok := m.(*pb.TranscriptLiveResponse); ok {
return e.Send(x)
}
return nil
}
func (e *embedBackendAudioTranscriptionLiveStream) RecvMsg(m any) error {
// gRPC bidi streaming uses Recv() directly; RecvMsg is unused on this path.
return nil
}
// embedBackendAudioTranscriptionLiveStreamClient is the caller-facing side.
// It mirrors the server-side stream over the same channels.
type embedBackendAudioTranscriptionLiveStreamClient struct {
ctx context.Context
reqs chan<- *pb.TranscriptLiveRequest
resps <-chan *pb.TranscriptLiveResponse
srvDone <-chan error
closeOnce bool
}
func (e *embedBackendAudioTranscriptionLiveStreamClient) Send(req *pb.TranscriptLiveRequest) error {
select {
case e.reqs <- req:
return nil
case <-e.ctx.Done():
return e.ctx.Err()
}
}
func (e *embedBackendAudioTranscriptionLiveStreamClient) Recv() (*pb.TranscriptLiveResponse, error) {
select {
case resp, ok := <-e.resps:
if !ok {
// Server-side finished. Surface its terminal error if any.
select {
case err := <-e.srvDone:
if err != nil {
return nil, err
}
default:
}
return nil, io.EOF
}
return resp, nil
case <-e.ctx.Done():
return nil, e.ctx.Err()
}
}
func (e *embedBackendAudioTranscriptionLiveStreamClient) CloseSend() error {
if e.closeOnce {
return nil
}
e.closeOnce = true
close(e.reqs)
return nil
}
func (e *embedBackendAudioTranscriptionLiveStreamClient) Context() context.Context { return e.ctx }
// embedBackendAudioToAudioStream is the in-process server-side handle for
// the bidirectional any-to-any audio RPC. Mirrors embedBackendAudioTransform
// Stream — the hosted server reads requests from `reqs` (closed by client
// when done sending) and writes responses to `resps`.
type embedBackendAudioToAudioStream struct {
ctx context.Context
reqs <-chan *pb.AudioToAudioRequest
resps chan<- *pb.AudioToAudioResponse
}
func (e *embedBackendAudioToAudioStream) Send(resp *pb.AudioToAudioResponse) error {
select {
case e.resps <- resp:
return nil
case <-e.ctx.Done():
return e.ctx.Err()
}
}
func (e *embedBackendAudioToAudioStream) Recv() (*pb.AudioToAudioRequest, error) {
select {
case req, ok := <-e.reqs:
if !ok {
return nil, io.EOF
}
return req, nil
case <-e.ctx.Done():
return nil, e.ctx.Err()
}
}
func (e *embedBackendAudioToAudioStream) SetHeader(md metadata.MD) error { return nil }
func (e *embedBackendAudioToAudioStream) SendHeader(md metadata.MD) error { return nil }
func (e *embedBackendAudioToAudioStream) SetTrailer(md metadata.MD) {}
func (e *embedBackendAudioToAudioStream) Context() context.Context { return e.ctx }
func (e *embedBackendAudioToAudioStream) SendMsg(m any) error {
if x, ok := m.(*pb.AudioToAudioResponse); ok {
return e.Send(x)
}
return nil
}
func (e *embedBackendAudioToAudioStream) RecvMsg(m any) error { return nil }
type embedBackendAudioToAudioStreamClient struct {
ctx context.Context
reqs chan<- *pb.AudioToAudioRequest
resps <-chan *pb.AudioToAudioResponse
srvDone <-chan error
closeOnce bool
}
func (e *embedBackendAudioToAudioStreamClient) Send(req *pb.AudioToAudioRequest) error {
select {
case e.reqs <- req:
return nil
case <-e.ctx.Done():
return e.ctx.Err()
}
}
func (e *embedBackendAudioToAudioStreamClient) Recv() (*pb.AudioToAudioResponse, error) {
select {
case resp, ok := <-e.resps:
if !ok {
// Server goroutine writes to srvDone immediately after closing
// resps; block (cap with ctx) so we don't race past a real error.
select {
case err := <-e.srvDone:
if err != nil {
return nil, err
}
case <-e.ctx.Done():
return nil, e.ctx.Err()
}
return nil, io.EOF
}
return resp, nil
case <-e.ctx.Done():
return nil, e.ctx.Err()
}
}
func (e *embedBackendAudioToAudioStreamClient) CloseSend() error {
if e.closeOnce {
return nil
}
e.closeOnce = true
close(e.reqs)
return nil
}
func (e *embedBackendAudioToAudioStreamClient) Context() context.Context { return e.ctx }
var _ pb.Backend_AudioTranscriptionStreamServer = new(embedBackendAudioTranscriptionStream)
type embedBackendAudioTranscriptionStream struct {
ctx context.Context
fn func(chunk *pb.TranscriptStreamResponse)
}
func (e *embedBackendAudioTranscriptionStream) Send(chunk *pb.TranscriptStreamResponse) error {
e.fn(chunk)
return nil
}
func (e *embedBackendAudioTranscriptionStream) SetHeader(md metadata.MD) error {
return nil
}
func (e *embedBackendAudioTranscriptionStream) SendHeader(md metadata.MD) error {
return nil
}
func (e *embedBackendAudioTranscriptionStream) SetTrailer(md metadata.MD) {
}
func (e *embedBackendAudioTranscriptionStream) Context() context.Context {
return e.ctx
}
func (e *embedBackendAudioTranscriptionStream) SendMsg(m any) error {
if x, ok := m.(*pb.TranscriptStreamResponse); ok {
return e.Send(x)
}
return nil
}
func (e *embedBackendAudioTranscriptionStream) RecvMsg(m any) error {
return nil
}
var _ pb.Backend_FineTuneProgressServer = new(embedBackendFineTuneProgressStream)
type embedBackendFineTuneProgressStream struct {
ctx context.Context
fn func(update *pb.FineTuneProgressUpdate)
}
func (e *embedBackendFineTuneProgressStream) Send(update *pb.FineTuneProgressUpdate) error {
e.fn(update)
return nil
}
func (e *embedBackendFineTuneProgressStream) SetHeader(md metadata.MD) error {
return nil
}
func (e *embedBackendFineTuneProgressStream) SendHeader(md metadata.MD) error {
return nil
}
func (e *embedBackendFineTuneProgressStream) SetTrailer(md metadata.MD) {
}
func (e *embedBackendFineTuneProgressStream) Context() context.Context {
return e.ctx
}
func (e *embedBackendFineTuneProgressStream) SendMsg(m any) error {
if x, ok := m.(*pb.FineTuneProgressUpdate); ok {
return e.Send(x)
}
return nil
}
func (e *embedBackendFineTuneProgressStream) RecvMsg(m any) error {
return nil
}
var _ pb.Backend_QuantizationProgressServer = new(embedBackendQuantizationProgressStream)
type embedBackendQuantizationProgressStream struct {
ctx context.Context
fn func(update *pb.QuantizationProgressUpdate)
}
func (e *embedBackendQuantizationProgressStream) Send(update *pb.QuantizationProgressUpdate) error {
e.fn(update)
return nil
}
func (e *embedBackendQuantizationProgressStream) SetHeader(md metadata.MD) error {
return nil
}
func (e *embedBackendQuantizationProgressStream) SendHeader(md metadata.MD) error {
return nil
}
func (e *embedBackendQuantizationProgressStream) SetTrailer(md metadata.MD) {
}
func (e *embedBackendQuantizationProgressStream) Context() context.Context {
return e.ctx
}
func (e *embedBackendQuantizationProgressStream) SendMsg(m any) error {
if x, ok := m.(*pb.QuantizationProgressUpdate); ok {
return e.Send(x)
}
return nil
}
func (e *embedBackendQuantizationProgressStream) RecvMsg(m any) error {
return nil
}
type embedBackendServerStream struct {
ctx context.Context
fn func(reply *pb.Reply)
}
func (e *embedBackendServerStream) Send(reply *pb.Reply) error {
e.fn(reply)
return nil
}
func (e *embedBackendServerStream) SetHeader(md metadata.MD) error {
return nil
}
func (e *embedBackendServerStream) SendHeader(md metadata.MD) error {
return nil
}
func (e *embedBackendServerStream) SetTrailer(md metadata.MD) {
}
func (e *embedBackendServerStream) Context() context.Context {
return e.ctx
}
func (e *embedBackendServerStream) SendMsg(m any) error {
if x, ok := m.(*pb.Reply); ok {
return e.Send(x)
}
return nil
}
func (e *embedBackendServerStream) RecvMsg(m any) error {
return nil
}
var _ pb.Backend_ForwardServer = new(embedBackendForwardStream)
var _ ForwardClient = new(embedBackendForwardStreamClient)
// embedBackendForwardStream is the server-side handle for an in-process
// Forward bidi stream. The hosted backend reads requests from `reqs`
// (closed by the client when done sending) and writes replies to
// `resps`.
type embedBackendForwardStream struct {
ctx context.Context
reqs <-chan *pb.ForwardRequest
resps chan<- *pb.ForwardReply
}
func (e *embedBackendForwardStream) Send(resp *pb.ForwardReply) error {
select {
case e.resps <- resp:
return nil
case <-e.ctx.Done():
return e.ctx.Err()
}
}
func (e *embedBackendForwardStream) Recv() (*pb.ForwardRequest, error) {
select {
case req, ok := <-e.reqs:
if !ok {
return nil, io.EOF
}
return req, nil
case <-e.ctx.Done():
return nil, e.ctx.Err()
}
}
func (e *embedBackendForwardStream) SetHeader(md metadata.MD) error { return nil }
func (e *embedBackendForwardStream) SendHeader(md metadata.MD) error { return nil }
func (e *embedBackendForwardStream) SetTrailer(md metadata.MD) {}
func (e *embedBackendForwardStream) Context() context.Context { return e.ctx }
func (e *embedBackendForwardStream) SendMsg(m any) error {
if x, ok := m.(*pb.ForwardReply); ok {
return e.Send(x)
}
return nil
}
func (e *embedBackendForwardStream) RecvMsg(m any) error { return nil }
// embedBackendForwardStreamClient is the caller-facing side. Mirrors
// the server-side stream over the same channels.
type embedBackendForwardStreamClient struct {
ctx context.Context
reqs chan<- *pb.ForwardRequest
resps <-chan *pb.ForwardReply
srvDone <-chan error
once sync.Once
}
func (e *embedBackendForwardStreamClient) Send(req *pb.ForwardRequest) error {
select {
case e.reqs <- req:
return nil
case <-e.ctx.Done():
return e.ctx.Err()
}
}
func (e *embedBackendForwardStreamClient) Recv() (*pb.ForwardReply, error) {
select {
case resp, ok := <-e.resps:
if !ok {
select {
case err := <-e.srvDone:
if err != nil {
return nil, err
}
default:
}
return nil, io.EOF
}
return resp, nil
case <-e.ctx.Done():
return nil, e.ctx.Err()
}
}
func (e *embedBackendForwardStreamClient) CloseSend() error {
e.once.Do(func() { close(e.reqs) })
return nil
}
func (e *embedBackendForwardStreamClient) Context() context.Context { return e.ctx }