chore(model gallery): 🤖 add 1 new models via gallery agent (#9202)

chore(model gallery): 🤖 add new models via gallery agent

Signed-off-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Co-authored-by: mudler <2420543+mudler@users.noreply.github.com>

.github/gallery-agent/agent.go

@@ -133,6 +133,7 @@ func getRealReadme(ctx context.Context, repository string) (string, error) {
 	result, err := cogito.ExecuteTools(llm, fragment,
 		cogito.WithIterations(3),
 		cogito.WithMaxAttempts(3),
+		cogito.DisableSinkState,
 		cogito.WithTools(&HFReadmeTool{client: hfapi.NewClient()}))
 	if err != nil {
 		return "", err

.github/gallery-agent/gallery.go

@@ -79,7 +79,20 @@ func generateYAMLEntry(model ProcessedModel, quantization string) string {
 	description = cleanTextContent(description)
 	formattedDescription := formatTextContent(description)
 
-	configFile := formatTextContent(modelConfig.ConfigFile)
+	// Strip name and description from config file since they are
+	// already present at the gallery entry level and should not
+	// appear under overrides.
+	configFileContent := modelConfig.ConfigFile
+	var cfgMap map[string]any
+	if err := yaml.Unmarshal([]byte(configFileContent), &cfgMap); err == nil {
+		delete(cfgMap, "name")
+		delete(cfgMap, "description")
+		if cleaned, err := yaml.Marshal(cfgMap); err == nil {
+			configFileContent = string(cleaned)
+		}
+	}
+
+	configFile := formatTextContent(configFileContent)
 
 	filesYAML, _ := yaml.Marshal(modelConfig.Files)
 

.github/gallery-agent/testing.go

@@ -17,7 +17,7 @@ func runSyntheticMode() error {
 	fmt.Printf("Generating %d synthetic models for testing...\n", numModels)
 
 	var models []ProcessedModel
-	for i := range numModels {
+	for range numModels {
 		model := generator.GenerateProcessedModel()
 		models = append(models, model)
 		fmt.Printf("Generated synthetic model: %s\n", model.ModelID)

.github/workflows/gallery-agent.yaml

@@ -55,7 +55,7 @@ jobs:
       - name: Run gallery agent
         env:
           #OPENAI_MODEL: ${{ secrets.OPENAI_MODEL }}
-          OPENAI_MODE: Qwen3.5-2B-GGUF
+          OPENAI_MODEL: Qwen3.5-2B-GGUF
           OPENAI_BASE_URL: "http://localhost:8080"
           OPENAI_KEY: ${{ secrets.OPENAI_KEY }}
           #OPENAI_BASE_URL: ${{ secrets.OPENAI_BASE_URL }}

backend/cpp/llama-cpp/Makefile

@@ -1,5 +1,5 @@
 
-LLAMA_VERSION?=0fcb3760b2b9a3a496ef14621a7e4dad7a8df90f
+LLAMA_VERSION?=95a6ebabb277c4cc18247e7bc2a5502133caca63
 LLAMA_REPO?=https://github.com/ggerganov/llama.cpp
 
 CMAKE_ARGS?=

backend/go/stablediffusion-ggml/Makefile

@@ -8,7 +8,7 @@ JOBS?=$(shell nproc --ignore=1)
 
 # stablediffusion.cpp (ggml)
 STABLEDIFFUSION_GGML_REPO?=https://github.com/leejet/stable-diffusion.cpp
-STABLEDIFFUSION_GGML_VERSION?=09b12d5f6d51d862749e8e0ee8baac8f012089e2
+STABLEDIFFUSION_GGML_VERSION?=87ecb95cbc65dc8e58e3d88f4f4a59a0939796f5
 
 CMAKE_ARGS+=-DGGML_MAX_NAME=128
 

gallery/index.yaml

@@ -1,4 +1,38 @@
 ---
+- name: "qwen3.5-35b-a3b-apex"
+  url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
+  urls:
+    - https://huggingface.co/mudler/Qwen3.5-35B-A3B-APEX-GGUF
+  description: |
+    Describe the model in a clear and concise way that can be shared in a model gallery.
+  overrides:
+    backend: llama-cpp
+    function:
+      automatic_tool_parsing_fallback: true
+      grammar:
+        disable: true
+    known_usecases:
+      - chat
+    mmproj: llama-cpp/mmproj/Qwen3.5-35B-A3B-APEX-GGUF/mmproj-F16.gguf
+    options:
+      - use_jinja:true
+    parameters:
+      min_p: 0
+      model: llama-cpp/models/Qwen3.5-35B-A3B-APEX-GGUF/Qwen3.5-35B-A3B-APEX-Quality.gguf
+      presence_penalty: 1.5
+      repeat_penalty: 1
+      temperature: 0.7
+      top_k: 20
+      top_p: 0.8
+    template:
+      use_tokenizer_template: true
+  files:
+    - filename: llama-cpp/mmproj/Qwen3.5-35B-A3B-APEX-GGUF/mmproj-F16.gguf
+      sha256: a516ab92e8240da4734d68352bdfba84c16e830ee40010b8fac80d69c77272ff
+      uri: https://huggingface.co/mudler/Qwen3.5-35B-A3B-APEX-GGUF/resolve/main/mmproj-F16.gguf
+    - filename: llama-cpp/models/Qwen3.5-35B-A3B-APEX-GGUF/Qwen3.5-35B-A3B-APEX-Quality.gguf
+      sha256: 50887b60c77ee5c95bc3657814ae993abcab7b2d71868b9af1e84d6badd09a57
+      uri: https://huggingface.co/mudler/Qwen3.5-35B-A3B-APEX-GGUF/resolve/main/Qwen3.5-35B-A3B-APEX-Quality.gguf
 - name: "qwen_qwen3.5-35b-a3b"
   url: "github:mudler/LocalAI/gallery/virtual.yaml@master"
   urls: