mirror of
https://github.com/mudler/LocalAI.git
synced 2026-05-17 04:56:52 -04:00
* 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 toe65d3e1fwhich 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 to85edf9d2. 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>
119 lines
3.6 KiB
Go
119 lines
3.6 KiB
Go
package cli
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"os"
|
|
"path/filepath"
|
|
"strconv"
|
|
"strings"
|
|
|
|
"github.com/mudler/LocalAI/core/backend"
|
|
cliContext "github.com/mudler/LocalAI/core/cli/context"
|
|
"github.com/mudler/LocalAI/core/config"
|
|
"github.com/mudler/LocalAI/pkg/model"
|
|
"github.com/mudler/LocalAI/pkg/system"
|
|
"github.com/mudler/xlog"
|
|
)
|
|
|
|
type SoundGenerationCMD struct {
|
|
Text []string `arg:""`
|
|
|
|
Backend string `short:"b" required:"" help:"Backend to run the SoundGeneration model"`
|
|
Model string `short:"m" required:"" help:"Model name to run the SoundGeneration"`
|
|
Duration string `short:"d" help:"If specified, the length of audio to generate in seconds"`
|
|
Temperature string `short:"t" help:"If specified, the temperature of the generation"`
|
|
InputFile string `short:"i" help:"If specified, the input file to condition generation upon"`
|
|
InputFileSampleDivisor string `short:"f" help:"If InputFile and this divisor is specified, the first portion of the sample file will be used"`
|
|
DoSample bool `short:"s" default:"true" help:"Enables sampling from the model. Better quality at the cost of speed. Defaults to enabled."`
|
|
OutputFile string `short:"o" type:"path" help:"The path to write the output wav file"`
|
|
ModelsPath string `env:"LOCALAI_MODELS_PATH,MODELS_PATH" type:"path" default:"${basepath}/models" help:"Path containing models used for inferencing" group:"storage"`
|
|
ExternalGRPCBackends []string `env:"LOCALAI_EXTERNAL_GRPC_BACKENDS,EXTERNAL_GRPC_BACKENDS" help:"A list of external grpc backends" group:"backends"`
|
|
}
|
|
|
|
func parseToFloat32Ptr(input string) *float32 {
|
|
f, err := strconv.ParseFloat(input, 32)
|
|
if err != nil {
|
|
return nil
|
|
}
|
|
f2 := float32(f)
|
|
return &f2
|
|
}
|
|
|
|
func parseToInt32Ptr(input string) *int32 {
|
|
i, err := strconv.ParseInt(input, 10, 32)
|
|
if err != nil {
|
|
return nil
|
|
}
|
|
i2 := int32(i)
|
|
return &i2
|
|
}
|
|
|
|
func (t *SoundGenerationCMD) Run(ctx *cliContext.Context) error {
|
|
outputFile := t.OutputFile
|
|
outputDir := os.TempDir()
|
|
if outputFile != "" {
|
|
outputDir = filepath.Dir(outputFile)
|
|
}
|
|
text := strings.Join(t.Text, " ")
|
|
|
|
systemState, err := system.GetSystemState(
|
|
system.WithModelPath(t.ModelsPath),
|
|
)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
externalBackends := make(map[string]string)
|
|
// split ":" to get backend name and the uri
|
|
for _, v := range t.ExternalGRPCBackends {
|
|
backend := v[:strings.IndexByte(v, ':')]
|
|
uri := v[strings.IndexByte(v, ':')+1:]
|
|
externalBackends[backend] = uri
|
|
}
|
|
|
|
opts := &config.ApplicationConfig{
|
|
SystemState: systemState,
|
|
Context: context.Background(),
|
|
GeneratedContentDir: outputDir,
|
|
ExternalGRPCBackends: externalBackends,
|
|
}
|
|
ml := model.NewModelLoader(systemState)
|
|
|
|
defer func() {
|
|
err := ml.StopAllGRPC()
|
|
if err != nil {
|
|
xlog.Error("unable to stop all grpc processes", "error", err)
|
|
}
|
|
}()
|
|
|
|
options := config.ModelConfig{}
|
|
options.SetDefaults()
|
|
options.Backend = t.Backend
|
|
options.Model = t.Model
|
|
|
|
var inputFile *string
|
|
if t.InputFile != "" {
|
|
inputFile = &t.InputFile
|
|
}
|
|
|
|
filePath, _, err := backend.SoundGeneration(context.Background(), text,
|
|
parseToFloat32Ptr(t.Duration), parseToFloat32Ptr(t.Temperature), &t.DoSample,
|
|
inputFile, parseToInt32Ptr(t.InputFileSampleDivisor),
|
|
nil, "", "", nil, "", "", "", nil,
|
|
ml, opts, options)
|
|
|
|
if err != nil {
|
|
return err
|
|
}
|
|
if outputFile != "" {
|
|
if err := os.Rename(filePath, outputFile); err != nil {
|
|
return err
|
|
}
|
|
fmt.Printf("Generate file %s\n", outputFile)
|
|
} else {
|
|
fmt.Printf("Generate file %s\n", filePath)
|
|
}
|
|
return nil
|
|
}
|