fix(model): deterministic, file-type-filtered backend auto-detect (#9287)

When a model config declares no explicit `backend:`, Load() fell into a
trial loop built by ranging the external-backends Go map (random order)
with no filtering, returning the first backend whose gRPC LoadModel
succeeded. An unrelated installed backend - e.g. the "opus" audio codec -
could therefore win a GGUF/LLM model load, so a model that should run on
llama.cpp wrongly tried to use opus.

Extract the candidate selection into a pure, testable function
SelectAutoLoadBackends that:

  - sorts the candidate list deterministically (no more map-order
    nondeterminism), and
  - for a `.gguf` model, filters to LLM-capable backends (via
    core/config.BackendCapabilities) and puts llama-cpp first, so an
    incompatible audio/codec/image backend can never win the trial loop.

If filtering would leave zero candidates, the full sorted set is returned
unchanged, so a previously-loadable model is never made unloadable.

Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
Assisted-by: claude:claude-opus-4-8 [Claude Code]
Signed-off-by: Ettore Di Giacinto <mudler@localai.io>

Author: mudler

pkg/model/autoload.go

@@ -0,0 +1,99 @@
+package model
+
+import (
+	"slices"
+	"sort"
+	"strings"
+
+	"github.com/mudler/LocalAI/core/config"
+)
+
+// preferredGGUFBackend is tried first when auto-detecting the backend for a
+// GGUF model, since GGUF is overwhelmingly llama.cpp's native format.
+const preferredGGUFBackend = "llama-cpp"
+
+// llmCapableUsecases are the BackendCapabilities usecases that signal a backend
+// can serve a text/LLM GGUF model. A GGUF model that declares no explicit
+// backend must only be auto-tried against backends carrying one of these
+// usecases - never against audio/codec/image backends (e.g. opus) that happen
+// to be installed alongside it (see issue #9287).
+var llmCapableUsecases = []string{
+	config.UsecaseChat,
+	config.UsecaseCompletion,
+	config.UsecaseEdit,
+	config.UsecaseEmbeddings,
+}
+
+// SelectAutoLoadBackends returns the ordered, deterministic list of backend
+// names to try when loading a model that declares no explicit backend.
+//
+// available is the set of installed backend names (unordered, as it comes from a
+// Go map). modelFile is the model file name/path (may be empty).
+//
+// The trial loop in (*ModelLoader).Load picks the first backend whose gRPC
+// LoadModel succeeds, so the order and membership of this list directly decide
+// which backend wins. The previous implementation ranged a Go map (random
+// order) with no filtering, so an unrelated installed backend such as the
+// "opus" audio codec could win a GGUF/LLM model load (#9287).
+//
+// Behaviour:
+//   - The result is always deterministically ordered, so auto-detect no longer
+//     depends on map iteration order.
+//   - For a GGUF model file the list is filtered to LLM-capable backends and
+//     llama-cpp is placed first, so an incompatible audio/codec/image backend
+//     can never win the trial loop.
+//   - If filtering would leave no candidate, the full sorted set is returned
+//     instead, so a model that previously loaded never becomes unloadable.
+func SelectAutoLoadBackends(available []string, modelFile string) []string {
+	sorted := append([]string(nil), available...)
+	sort.Strings(sorted)
+
+	if !isGGUFModelFile(modelFile) {
+		return sorted
+	}
+
+	filtered := make([]string, 0, len(sorted))
+	hasLlama := false
+	for _, b := range sorted {
+		if b == preferredGGUFBackend {
+			hasLlama = true
+			continue // added explicitly first below
+		}
+		if isLLMCapableBackend(b) {
+			filtered = append(filtered, b)
+		}
+	}
+	if hasLlama {
+		filtered = append([]string{preferredGGUFBackend}, filtered...)
+	}
+
+	if len(filtered) == 0 {
+		// Conservative fallback: no known LLM-capable backend is installed, so
+		// rather than refuse to load, fall back to the previous behaviour of
+		// trying every installed backend (now at least in a deterministic order).
+		return sorted
+	}
+	return filtered
+}
+
+func isGGUFModelFile(modelFile string) bool {
+	return strings.HasSuffix(strings.ToLower(modelFile), ".gguf")
+}
+
+// isLLMCapableBackend reports whether a backend is known to serve text/LLM
+// models. Backends absent from the capability map (unknown) are treated as
+// not LLM-capable here: for GGUF auto-detection we only want backends we can
+// positively confirm handle LLMs, and the zero-candidate fallback keeps unknown
+// setups working.
+func isLLMCapableBackend(name string) bool {
+	capability := config.GetBackendCapability(name)
+	if capability == nil {
+		return false
+	}
+	for _, u := range capability.PossibleUsecases {
+		if slices.Contains(llmCapableUsecases, u) {
+			return true
+		}
+	}
+	return false
+}

pkg/model/autoload_test.go

@@ -0,0 +1,46 @@
+package model_test
+
+import (
+	"github.com/mudler/LocalAI/pkg/model"
+
+	. "github.com/onsi/ginkgo/v2"
+	. "github.com/onsi/gomega"
+)
+
+var _ = Describe("SelectAutoLoadBackends (#9287)", func() {
+	Describe("GGUF model auto-detection", func() {
+		It("excludes incompatible audio/codec backends (e.g. opus) for a .gguf model", func() {
+			// Regression for #9287: installing an unrelated audio backend like
+			// "opus" must never win the GGUF auto-detect trial loop.
+			got := model.SelectAutoLoadBackends([]string{"opus", "llama-cpp"}, "Qwen3.5-9b.gguf")
+			Expect(got).NotTo(ContainElement("opus"))
+			Expect(got).To(ContainElement("llama-cpp"))
+		})
+
+		It("places llama-cpp first for a .gguf model", func() {
+			got := model.SelectAutoLoadBackends([]string{"vllm", "opus", "llama-cpp"}, "model.gguf")
+			Expect(got).NotTo(BeEmpty())
+			Expect(got[0]).To(Equal("llama-cpp"))
+		})
+
+		It("is deterministic regardless of input ordering", func() {
+			a := model.SelectAutoLoadBackends([]string{"opus", "vllm", "llama-cpp", "whisper"}, "m.gguf")
+			b := model.SelectAutoLoadBackends([]string{"whisper", "llama-cpp", "vllm", "opus"}, "m.gguf")
+			Expect(a).To(Equal(b))
+		})
+
+		It("falls back to the full sorted set when filtering leaves no candidate", func() {
+			// No LLM-capable backend installed: never make a previously-loadable
+			// model unloadable, return the original set (sorted).
+			got := model.SelectAutoLoadBackends([]string{"opus"}, "model.gguf")
+			Expect(got).To(Equal([]string{"opus"}))
+		})
+	})
+
+	Describe("non-GGUF model auto-detection", func() {
+		It("returns a deterministic (sorted) set without filtering", func() {
+			got := model.SelectAutoLoadBackends([]string{"opus", "llama-cpp", "diffusers"}, "model-dir")
+			Expect(got).To(Equal([]string{"diffusers", "llama-cpp", "opus"}))
+		})
+	})
+})

pkg/model/initializers.go

@@ -438,14 +438,17 @@ func (ml *ModelLoader) Load(opts ...Option) (grpc.Backend, error) {
 	// Otherwise scan for backends in the asset directory
 	var err error
 
-	// get backends embedded in the binary
-	autoLoadBackends := []string{}
-
-	// append externalBackends supplied by the user via the CLI
+	// Collect the installed/external backends (the map is unordered).
+	available := []string{}
 	for b := range ml.GetAllExternalBackends(o) {
-		autoLoadBackends = append(autoLoadBackends, b)
+		available = append(available, b)
 	}
 
+	// Build a deterministic, file-type-filtered candidate list so an
+	// incompatible backend (e.g. an audio codec like opus) can never win the
+	// trial loop for a GGUF/LLM model. See SelectAutoLoadBackends / #9287.
+	autoLoadBackends := SelectAutoLoadBackends(available, o.model)
+
 	if len(autoLoadBackends) == 0 {
 		xlog.Error("No backends found")
 		return nil, fmt.Errorf("no backends found")