fix: include model name in mmproj file path to prevent model isolation (mudler#8937) (mudler#8940)

* fix: include model name in mmproj file path to prevent model isolation issues

This fix addresses issue mudler#8937 where different models with mmproj files
having the same filename (e.g., mmproj-F32.gguf) would overwrite each other.

By including the model name in the path (llama-cpp/mmproj/<model-name>/<filename>),
each model's mmproj files are now stored in separate directories, preventing
the collision that caused conversations to fail when switching between models.

Fixes mudler#8937

Signed-off-by: LocalAI Bot <localai-bot@example.com>

* test: update test expectations for model name in mmproj path

The test file had hardcoded expectations for the old mmproj path format.
Updated the test expectations to include the model name subdirectory
to match the new path structure introduced in the fix.

Fixes CI failures on tests-apple and tests-linux

* fix: add model name to model path for consistency with mmproj path

This change makes the model path consistent with the mmproj path by
including the model name subdirectory in both paths:
- mmproj: llama-cpp/mmproj/<model-name>/<filename>
- model: llama-cpp/models/<model-name>/<filename>

This addresses the reviewer's feedback that the model config generation
needs to correctly reference the mmproj file path.

Fixes the issue where the model path didn't include the model name
subdirectory while the mmproj path did.

Signed-off-by: team-coding-agent-1 <team-coding-agent-1@localai.dev>

---------

Signed-off-by: LocalAI Bot <localai-bot@example.com>
Signed-off-by: team-coding-agent-1 <team-coding-agent-1@localai.dev>
Co-authored-by: team-coding-agent-1 <team-coding-agent-1@localai.dev>

Author: localai-bot

core/gallery/importers/importers_test.go

@@ -25,7 +25,7 @@ var _ = Describe("DiscoverModelConfig", func() {
 			Expect(modelConfig.Description).To(Equal("Imported from https://huggingface.co/mudler/LocalAI-functioncall-qwen2.5-7b-v0.5-Q4_K_M-GGUF"), fmt.Sprintf("Model config: %+v", modelConfig))
 			Expect(modelConfig.ConfigFile).To(ContainSubstring("backend: llama-cpp"), fmt.Sprintf("Model config: %+v", modelConfig))
 			Expect(len(modelConfig.Files)).To(Equal(1), fmt.Sprintf("Model config: %+v", modelConfig))
-			Expect(modelConfig.Files[0].Filename).To(Equal("llama-cpp/models/localai-functioncall-qwen2.5-7b-v0.5-q4_k_m.gguf"), fmt.Sprintf("Model config: %+v", modelConfig))
+			Expect(modelConfig.Files[0].Filename).To(Equal("llama-cpp/models/LocalAI-functioncall-qwen2.5-7b-v0.5-Q4_K_M-GGUF/localai-functioncall-qwen2.5-7b-v0.5-q4_k_m.gguf"), fmt.Sprintf("Model config: %+v", modelConfig))
 			Expect(modelConfig.Files[0].URI).To(Equal("https://huggingface.co/mudler/LocalAI-functioncall-qwen2.5-7b-v0.5-Q4_K_M-GGUF/resolve/main/localai-functioncall-qwen2.5-7b-v0.5-q4_k_m.gguf"), fmt.Sprintf("Model config: %+v", modelConfig))
 			Expect(modelConfig.Files[0].SHA256).To(Equal("4e7b7fe1d54b881f1ef90799219dc6cc285d29db24f559c8998d1addb35713d4"), fmt.Sprintf("Model config: %+v", modelConfig))
 		})
@@ -40,13 +40,13 @@ var _ = Describe("DiscoverModelConfig", func() {
 			Expect(modelConfig.Name).To(Equal("Qwen3-VL-2B-Instruct-GGUF"), fmt.Sprintf("Model config: %+v", modelConfig))
 			Expect(modelConfig.Description).To(Equal("Imported from https://huggingface.co/Qwen/Qwen3-VL-2B-Instruct-GGUF"), fmt.Sprintf("Model config: %+v", modelConfig))
 			Expect(modelConfig.ConfigFile).To(ContainSubstring("backend: llama-cpp"), fmt.Sprintf("Model config: %+v", modelConfig))
-			Expect(modelConfig.ConfigFile).To(ContainSubstring("mmproj: llama-cpp/mmproj/mmproj-Qwen3VL-2B-Instruct-Q8_0.gguf"), fmt.Sprintf("Model config: %+v", modelConfig))
-			Expect(modelConfig.ConfigFile).To(ContainSubstring("model: llama-cpp/models/Qwen3VL-2B-Instruct-Q4_K_M.gguf"), fmt.Sprintf("Model config: %+v", modelConfig))
+			Expect(modelConfig.ConfigFile).To(ContainSubstring("mmproj: llama-cpp/mmproj/Qwen3-VL-2B-Instruct-GGUF/mmproj-Qwen3VL-2B-Instruct-Q8_0.gguf"), fmt.Sprintf("Model config: %+v", modelConfig))
+			Expect(modelConfig.ConfigFile).To(ContainSubstring("model: llama-cpp/models/Qwen3-VL-2B-Instruct-GGUF/Qwen3VL-2B-Instruct-Q4_K_M.gguf"), fmt.Sprintf("Model config: %+v", modelConfig))
 			Expect(len(modelConfig.Files)).To(Equal(2), fmt.Sprintf("Model config: %+v", modelConfig))
-			Expect(modelConfig.Files[0].Filename).To(Equal("llama-cpp/models/Qwen3VL-2B-Instruct-Q4_K_M.gguf"), fmt.Sprintf("Model config: %+v", modelConfig))
+			Expect(modelConfig.Files[0].Filename).To(Equal("llama-cpp/models/Qwen3-VL-2B-Instruct-GGUF/Qwen3VL-2B-Instruct-Q4_K_M.gguf"), fmt.Sprintf("Model config: %+v", modelConfig))
 			Expect(modelConfig.Files[0].URI).To(Equal("https://huggingface.co/Qwen/Qwen3-VL-2B-Instruct-GGUF/resolve/main/Qwen3VL-2B-Instruct-Q4_K_M.gguf"), fmt.Sprintf("Model config: %+v", modelConfig))
 			Expect(modelConfig.Files[0].SHA256).ToNot(BeEmpty(), fmt.Sprintf("Model config: %+v", modelConfig))
-			Expect(modelConfig.Files[1].Filename).To(Equal("llama-cpp/mmproj/mmproj-Qwen3VL-2B-Instruct-Q8_0.gguf"), fmt.Sprintf("Model config: %+v", modelConfig))
+			Expect(modelConfig.Files[1].Filename).To(Equal("llama-cpp/mmproj/Qwen3-VL-2B-Instruct-GGUF/mmproj-Qwen3VL-2B-Instruct-Q8_0.gguf"), fmt.Sprintf("Model config: %+v", modelConfig))
 			Expect(modelConfig.Files[1].URI).To(Equal("https://huggingface.co/Qwen/Qwen3-VL-2B-Instruct-GGUF/resolve/main/mmproj-Qwen3VL-2B-Instruct-Q8_0.gguf"), fmt.Sprintf("Model config: %+v", modelConfig))
 			Expect(modelConfig.Files[1].SHA256).ToNot(BeEmpty(), fmt.Sprintf("Model config: %+v", modelConfig))
 		})
@@ -61,13 +61,13 @@ var _ = Describe("DiscoverModelConfig", func() {
 			Expect(modelConfig.Name).To(Equal("Qwen3-VL-2B-Instruct-GGUF"), fmt.Sprintf("Model config: %+v", modelConfig))
 			Expect(modelConfig.Description).To(Equal("Imported from https://huggingface.co/Qwen/Qwen3-VL-2B-Instruct-GGUF"), fmt.Sprintf("Model config: %+v", modelConfig))
 			Expect(modelConfig.ConfigFile).To(ContainSubstring("backend: llama-cpp"), fmt.Sprintf("Model config: %+v", modelConfig))
-			Expect(modelConfig.ConfigFile).To(ContainSubstring("mmproj: llama-cpp/mmproj/mmproj-Qwen3VL-2B-Instruct-F16.gguf"), fmt.Sprintf("Model config: %+v", modelConfig))
-			Expect(modelConfig.ConfigFile).To(ContainSubstring("model: llama-cpp/models/Qwen3VL-2B-Instruct-Q8_0.gguf"), fmt.Sprintf("Model config: %+v", modelConfig))
+			Expect(modelConfig.ConfigFile).To(ContainSubstring("mmproj: llama-cpp/mmproj/Qwen3-VL-2B-Instruct-GGUF/mmproj-Qwen3VL-2B-Instruct-F16.gguf"), fmt.Sprintf("Model config: %+v", modelConfig))
+			Expect(modelConfig.ConfigFile).To(ContainSubstring("model: llama-cpp/models/Qwen3-VL-2B-Instruct-GGUF/Qwen3VL-2B-Instruct-Q8_0.gguf"), fmt.Sprintf("Model config: %+v", modelConfig))
 			Expect(len(modelConfig.Files)).To(Equal(2), fmt.Sprintf("Model config: %+v", modelConfig))
-			Expect(modelConfig.Files[0].Filename).To(Equal("llama-cpp/models/Qwen3VL-2B-Instruct-Q8_0.gguf"), fmt.Sprintf("Model config: %+v", modelConfig))
+			Expect(modelConfig.Files[0].Filename).To(Equal("llama-cpp/models/Qwen3-VL-2B-Instruct-GGUF/Qwen3VL-2B-Instruct-Q8_0.gguf"), fmt.Sprintf("Model config: %+v", modelConfig))
 			Expect(modelConfig.Files[0].URI).To(Equal("https://huggingface.co/Qwen/Qwen3-VL-2B-Instruct-GGUF/resolve/main/Qwen3VL-2B-Instruct-Q8_0.gguf"), fmt.Sprintf("Model config: %+v", modelConfig))
 			Expect(modelConfig.Files[0].SHA256).ToNot(BeEmpty(), fmt.Sprintf("Model config: %+v", modelConfig))
-			Expect(modelConfig.Files[1].Filename).To(Equal("llama-cpp/mmproj/mmproj-Qwen3VL-2B-Instruct-F16.gguf"), fmt.Sprintf("Model config: %+v", modelConfig))
+			Expect(modelConfig.Files[1].Filename).To(Equal("llama-cpp/mmproj/Qwen3-VL-2B-Instruct-GGUF/mmproj-Qwen3VL-2B-Instruct-F16.gguf"), fmt.Sprintf("Model config: %+v", modelConfig))
 			Expect(modelConfig.Files[1].URI).To(Equal("https://huggingface.co/Qwen/Qwen3-VL-2B-Instruct-GGUF/resolve/main/mmproj-Qwen3VL-2B-Instruct-F16.gguf"), fmt.Sprintf("Model config: %+v", modelConfig))
 			Expect(modelConfig.Files[1].SHA256).ToNot(BeEmpty(), fmt.Sprintf("Model config: %+v", modelConfig))
 		})

core/gallery/importers/llama-cpp.go

@@ -184,7 +184,7 @@ func (i *LlamaCPPImporter) Import(details Details) (gallery.ModelConfig, error)
 			if strings.Contains(strings.ToLower(file.Path), "mmproj") {
 				lastMMProjFile = &gallery.File{
 					URI:      file.URL,
-					Filename: filepath.Join("llama-cpp", "mmproj", filepath.Base(file.Path)),
+					Filename: filepath.Join("llama-cpp", "mmproj", name, filepath.Base(file.Path)),
 					SHA256:   file.SHA256,
 				}
 				if slices.ContainsFunc(mmprojQuantsList, func(quant string) bool {
@@ -196,7 +196,7 @@ func (i *LlamaCPPImporter) Import(details Details) (gallery.ModelConfig, error)
 			} else if strings.HasSuffix(strings.ToLower(file.Path), "gguf") {
 				lastGGUFFile = &gallery.File{
 					URI:      file.URL,
-					Filename: filepath.Join("llama-cpp", "models", filepath.Base(file.Path)),
+					Filename: filepath.Join("llama-cpp", "models", name, filepath.Base(file.Path)),
 					SHA256:   file.SHA256,
 				}
 				// get the files of the prefered quants