mirror of
https://github.com/mudler/LocalAI.git
synced 2026-07-30 18:09:05 -04:00
1cd7d63c7b
#10970 gave the four PredictOptions RPCs a model-identity check so a backend reached through a stale distributed route rejects the request instead of answering from whatever model it holds (#10952). Every other modality shares that exposure: the route is cached by host:port, a worker can recycle a stopped backend's port for another model's backend, and a liveness-only probe cannot tell a stale row from a valid one. Extends the same mechanism to the 21 remaining request messages that reach a backend through the router, using the pattern #10970 established rather than a parallel one: - proto: ModelIdentity on each modality request message. - controller: populated from ModelConfig.Model at the call site that also builds ModelOptions, so load-time and request-time values are equal by construction. - backends: one generic guard in pkg/grpc/server.go (27 Go backends), the method set in backend/python/common (36 Python backends), llama-cpp (AudioTranscription/Stream, Rerank, Score) and privacy-filter (TokenClassify). - reconcile already drops the stale row on IsModelMismatch; no change. TTSRequest and SoundGenerationRequest get a SEPARATE ModelIdentity field rather than reusing their existing `model`: FileStagingClient rewrites `model` to a worker-local path, so comparing it would reject valid requests in exactly the configuration this guards. AudioEncode/AudioDecode are deliberately left unguarded: the opus codec backend is loaded from a literal rather than a ModelConfig, so no value carries the equality guarantee the comparison depends on. The four bidirectional stream RPCs are out of scope; they bypass reconcile. Empty means skip on both sides, so an old controller, an old backend, and the bare request structs in tests/e2e-backends all keep working. Assisted-by: Claude Code:claude-opus-4-8 [Read] [Edit] [Bash] Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io>
98 lines
2.9 KiB
Go
98 lines
2.9 KiB
Go
package backend
|
|
|
|
import (
|
|
"context"
|
|
"time"
|
|
|
|
"github.com/mudler/LocalAI/core/config"
|
|
"github.com/mudler/LocalAI/core/trace"
|
|
|
|
"github.com/mudler/LocalAI/pkg/grpc/proto"
|
|
model "github.com/mudler/LocalAI/pkg/model"
|
|
)
|
|
|
|
func ImageGeneration(ctx context.Context, height, width, step, seed int, positive_prompt, negative_prompt, src, dst string, loader *model.ModelLoader, modelConfig config.ModelConfig, appConfig *config.ApplicationConfig, refImages []string) (func() error, error) {
|
|
|
|
// model.WithContext(ctx) overrides the app-context default set in
|
|
// ModelOptions so distributed routing decisions reach the request's
|
|
// X-LocalAI-Node holder via distributedhdr.Stamp.
|
|
opts := ModelOptions(modelConfig, appConfig, model.WithContext(ctx))
|
|
inferenceModel, err := loader.Load(
|
|
opts...,
|
|
)
|
|
if err != nil {
|
|
recordModelLoadFailure(appConfig, modelConfig.Name, modelConfig.Backend, err, nil)
|
|
return nil, err
|
|
}
|
|
|
|
fn := func() error {
|
|
_, err := inferenceModel.GenerateImage(
|
|
ctx,
|
|
&proto.GenerateImageRequest{
|
|
// ModelIdentity is ModelConfig.Model — the SAME expression
|
|
// ModelOptions feeds to model.WithModel above, which the
|
|
// backend receives as ModelOptions.Model at LoadModel. Equal
|
|
// by construction, so the check cannot false-reject (#10952).
|
|
ModelIdentity: modelConfig.Model,
|
|
Height: int32(height),
|
|
Width: int32(width),
|
|
Step: int32(step),
|
|
Seed: int32(seed),
|
|
CLIPSkip: int32(modelConfig.Diffusers.ClipSkip),
|
|
PositivePrompt: positive_prompt,
|
|
NegativePrompt: negative_prompt,
|
|
Dst: dst,
|
|
Src: src,
|
|
EnableParameters: modelConfig.Diffusers.EnableParameters,
|
|
RefImages: refImages,
|
|
})
|
|
return err
|
|
}
|
|
|
|
if appConfig.EnableTracing {
|
|
trace.InitBackendTracingIfEnabled(appConfig.TracingMaxItems, appConfig.TracingMaxBodyBytes)
|
|
|
|
traceData := map[string]any{
|
|
"positive_prompt": positive_prompt,
|
|
"negative_prompt": negative_prompt,
|
|
"height": height,
|
|
"width": width,
|
|
"step": step,
|
|
"seed": seed,
|
|
"source_image": src,
|
|
"destination": dst,
|
|
}
|
|
|
|
startTime := time.Now()
|
|
originalFn := fn
|
|
fn = func() error {
|
|
err := originalFn()
|
|
duration := time.Since(startTime)
|
|
|
|
errStr := ""
|
|
if err != nil {
|
|
errStr = err.Error()
|
|
}
|
|
|
|
trace.RecordBackendTrace(trace.BackendTrace{
|
|
Timestamp: startTime,
|
|
Duration: duration,
|
|
Type: trace.BackendTraceImageGeneration,
|
|
ModelName: modelConfig.Name,
|
|
Backend: modelConfig.Backend,
|
|
Summary: trace.TruncateString(positive_prompt, 200),
|
|
Error: errStr,
|
|
Data: traceData,
|
|
})
|
|
|
|
return err
|
|
}
|
|
}
|
|
|
|
return fn, nil
|
|
}
|
|
|
|
// ImageGenerationFunc is a test-friendly indirection to call image generation logic.
|
|
// Tests can override this variable to provide a stub implementation.
|
|
var ImageGenerationFunc = ImageGeneration
|