Files
LocalAI/core/backend/soundgeneration.go
LocalAI [bot] 2be07f61da feat(whisper): honor client cancellation via ggml abort_callback (#9710)
* refactor(transcription): propagate request ctx through ModelTranscription*

Replaces context.Background() with the HTTP request ctx so client
disconnects start cancelling the gRPC call. No backend-side abort wiring
yet — that comes in a later commit. Pure plumbing.

Assisted-by: Claude:claude-haiku-4-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(cli): pass ctx to backend.ModelTranscription

Follow-up to e65d3e1f which threaded ctx through ModelTranscription
but missed the CLI caller. CLI commands have no request-scoped ctx,
so context.Background() is correct here.

Assisted-by: Claude:claude-haiku-4-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* refactor(audio): propagate request ctx into TTS, sound-gen, audio-transform

Same ctx-plumbing pattern applied to the rest of the audio path. CLI
callers use context.Background() since there is no request scope; HTTP
callers use c.Request().Context().

Assisted-by: Claude:claude-haiku-4-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* refactor(backend): propagate request ctx into biometric, detection, rerank, diarization paths

Replaces remaining context.Background() sites in core/backend with the
caller's ctx. After this commit, every core/backend/*.go entry point
threads the request ctx end-to-end to the gRPC client.

Assisted-by: Claude:claude-haiku-4-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* refactor(grpc): plumb ctx through AIModel.AudioTranscription{,Stream}

Adds context.Context as first parameter to the AIModel interface methods
that wrap whisper-style transcription. Server-side gRPC handler now
forwards the per-RPC ctx (server-streaming uses stream.Context()).
Whisper, Voxtral, vibevoice-cpp, and sherpa-onnx accept the parameter;
none uses it yet — the actual cancellation primitive lands in the next
commit so this is pure plumbing.

Assisted-by: Claude:claude-sonnet-4-6
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* feat(whisper): add abort_callback hook in the C++ bridge

Installs a std::atomic<int> flag, wires it into
whisper_full_params.abort_callback, and exposes a set_abort(int) C
symbol so Go can flip the flag from a goroutine watching the request
context. transcribe() now distinguishes abort (return 2) from real
whisper_full failure (return 1).

Assisted-by: Claude:claude-haiku-4-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* feat(whisper): register set_abort symbol in the purego loader

Adds the Go-side binding for the new C export so the next commit can
call CppSetAbort(1) from a watcher goroutine on ctx.Done().

Assisted-by: Claude:claude-haiku-4-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* feat(whisper): honor ctx cancellation and return codes.Canceled

A watcher goroutine watches ctx.Done() during AudioTranscription and
calls CppSetAbort(1) on cancel. whisper_full sees abort_callback return
true at the next compute graph step, returns non-zero, and the bridge
returns 2 -> AudioTranscription maps that to codes.Canceled.

Adds an opt-in test (gated on WHISPER_MODEL_PATH / WHISPER_AUDIO_PATH)
that asserts cancellation latency under 5s and proves the abort flag
resets cleanly so the next transcription succeeds.

Assisted-by: Claude:claude-sonnet-4-6
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(whisper): join the cancel watcher goroutine before returning

Follow-up to 85edf9d2. The previous commit used `defer close(done)` and
called the watcher "joined synchronously" — but close() only signals,
it does not block until the goroutine exits. That left a window where
a late CppSetAbort(1) from a cancelled call could land on the next
call, after its C-side g_abort reset but before whisper_full() began
polling the abort callback, corrupting the second transcription.

Switch to a sync.WaitGroup join so wg.Wait() blocks until the watcher
has actually returned from its select.

Assisted-by: Claude:claude-sonnet-4-6
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(whisper): short-circuit pre-cancelled ctx in AudioTranscription

If ctx is already Done() at entry, return codes.Canceled immediately
instead of running the full transcription. The C-side g_abort reset
happens at the start of transcribe() and would otherwise overwrite a
watcher-set abort flag from an already-cancelled ctx, producing a
spurious successful transcription on a request the client has already
abandoned.

Assisted-by: Claude:claude-haiku-4-5
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* fix(tests/distributed): update testLLM mock for new AudioTranscription signature

Phase B (93c48e19) added context.Context to AIModel.AudioTranscription
but missed the testLLM mock in tests/e2e/distributed. CI golangci-lint
caught it: *testLLM did not implement grpc.AIModel because the method
signature lacked the ctx parameter, which broke the distributed test
suite compilation and cascaded through every backend-build job that
runs `go build ./...`.

Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

* test(whisper): port cancellation test to Ginkgo/Gomega

Project policy (.agents/coding-style.md, enforced by golangci-lint
forbidigo) is that all Go tests must use Ginkgo v2 + Gomega — no
stdlib testing patterns (t.Skip, t.Fatalf, etc.). Convert the
cancellation test to a Describe/It block with Skip(...) for env
gating and Expect/HaveOccurred for assertions.

Same coverage: cancel mid-flight returns codes.Canceled within 5s and
a follow-up transcription succeeds, proving the C-side g_abort flag
resets cleanly.

Assisted-by: Claude:claude-opus-4-7
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

---------

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
2026-05-08 01:44:47 +02:00

152 lines
3.5 KiB
Go

package backend
import (
"context"
"fmt"
"os"
"path/filepath"
"time"
"github.com/mudler/LocalAI/core/config"
"github.com/mudler/LocalAI/core/trace"
"github.com/mudler/LocalAI/pkg/grpc/proto"
"github.com/mudler/LocalAI/pkg/model"
"github.com/mudler/LocalAI/pkg/utils"
)
func SoundGeneration(
ctx context.Context,
text string,
duration *float32,
temperature *float32,
doSample *bool,
sourceFile *string,
sourceDivisor *int32,
think *bool,
caption string,
lyrics string,
bpm *int32,
keyscale string,
language string,
timesignature string,
instrumental *bool,
loader *model.ModelLoader,
appConfig *config.ApplicationConfig,
modelConfig config.ModelConfig,
) (string, *proto.Result, error) {
opts := ModelOptions(modelConfig, appConfig)
soundGenModel, err := loader.Load(opts...)
if err != nil {
recordModelLoadFailure(appConfig, modelConfig.Name, modelConfig.Backend, err, nil)
return "", nil, err
}
if soundGenModel == nil {
return "", nil, fmt.Errorf("could not load sound generation model")
}
if err := os.MkdirAll(appConfig.GeneratedContentDir, 0750); err != nil {
return "", nil, fmt.Errorf("failed creating audio directory: %s", err)
}
audioDir := filepath.Join(appConfig.GeneratedContentDir, "audio")
if err := os.MkdirAll(audioDir, 0750); err != nil {
return "", nil, fmt.Errorf("failed creating audio directory: %s", err)
}
fileName := utils.GenerateUniqueFileName(audioDir, "sound_generation", ".wav")
filePath := filepath.Join(audioDir, fileName)
if filePath, err = filepath.Abs(filePath); err != nil {
return "", nil, fmt.Errorf("failed resolving sound generation path: %w", err)
}
req := &proto.SoundGenerationRequest{
Text: text,
Model: modelConfig.Model,
Dst: filePath,
Sample: doSample,
Duration: duration,
Temperature: temperature,
Src: sourceFile,
SrcDivisor: sourceDivisor,
}
if think != nil {
req.Think = think
}
if caption != "" {
req.Caption = &caption
}
if lyrics != "" {
req.Lyrics = &lyrics
}
if bpm != nil {
req.Bpm = bpm
}
if keyscale != "" {
req.Keyscale = &keyscale
}
if language != "" {
req.Language = &language
}
if timesignature != "" {
req.Timesignature = &timesignature
}
if instrumental != nil {
req.Instrumental = instrumental
}
var startTime time.Time
if appConfig.EnableTracing {
trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems)
startTime = time.Now()
}
res, err := soundGenModel.SoundGeneration(ctx, req)
if appConfig.EnableTracing {
errStr := ""
if err != nil {
errStr = err.Error()
} else if res != nil && !res.Success {
errStr = fmt.Sprintf("sound generation error: %s", res.Message)
}
summary := trace.TruncateString(text, 200)
if summary == "" && caption != "" {
summary = trace.TruncateString(caption, 200)
}
traceData := map[string]any{
"text": text,
"caption": caption,
"lyrics": lyrics,
}
if duration != nil {
traceData["duration"] = *duration
}
if temperature != nil {
traceData["temperature"] = *temperature
}
trace.RecordBackendTrace(trace.BackendTrace{
Timestamp: startTime,
Duration: time.Since(startTime),
Type: trace.BackendTraceSoundGeneration,
ModelName: modelConfig.Name,
Backend: modelConfig.Backend,
Summary: summary,
Error: errStr,
Data: traceData,
})
}
if err != nil {
return "", nil, err
}
if res != nil && !res.Success {
return "", nil, fmt.Errorf("error during sound generation: %s", res.Message)
}
return filePath, res, nil
}