Ci: do not run jobs for every branch

Signed-off-by: mudler <mudler@localai.io>

README.md

@@ -49,10 +49,10 @@ cd LocalAGI
 docker compose up
 
 # NVIDIA GPU setup
-docker compose -f docker-compose.nvidia.yaml up
+docker compose --profile nvidia up
 
 # Intel GPU setup (for Intel Arc and integrated GPUs)
-docker compose -f docker-compose.intel.yaml up
+docker compose --profile intel up
 
 # Start with a specific model (see available models in models.localai.io, or localai.io to use any model in huggingface)
 MODEL_NAME=gemma-3-12b-it docker compose up
@@ -61,40 +61,11 @@ MODEL_NAME=gemma-3-12b-it docker compose up
 MODEL_NAME=gemma-3-12b-it \
 MULTIMODAL_MODEL=minicpm-v-2_6 \
 IMAGE_MODEL=flux.1-dev \
-docker compose -f docker-compose.nvidia.yaml up
+docker compose --profile nvidia up
 ```
 
 Now you can access and manage your agents at [http://localhost:8080](http://localhost:8080)
 
-## 📚🆕 Local Stack Family
-
-🆕 LocalAI is now part of a comprehensive suite of AI tools designed to work together:
-
-<table>
-  <tr>
-    <td width="50%" valign="top">
-      <a href="https://github.com/mudler/LocalAI">
-        <img src="https://raw.githubusercontent.com/mudler/LocalAI/refs/heads/rebranding/core/http/static/logo_horizontal.png" width="300" alt="LocalAI Logo">
-      </a>
-    </td>
-    <td width="50%" valign="top">
-      <h3><a href="https://github.com/mudler/LocalRecall">LocalAI</a></h3>
-      <p>LocalAI is the free, Open Source OpenAI alternative. LocalAI act as a drop-in replacement REST API that's compatible with OpenAI API specifications for local AI inferencing. Does not require GPU.</p>
-    </td>
-  </tr>
-  <tr>
-    <td width="50%" valign="top">
-      <a href="https://github.com/mudler/LocalRecall">
-        <img src="https://raw.githubusercontent.com/mudler/LocalRecall/refs/heads/main/static/localrecall_horizontal.png" width="300" alt="LocalRecall Logo">
-      </a>
-    </td>
-    <td width="50%" valign="top">
-      <h3><a href="https://github.com/mudler/LocalRecall">LocalRecall</a></h3>
-      <p>A REST-ful API and knowledge base management system that provides persistent memory and storage capabilities for AI agents.</p>
-    </td>
-  </tr>
-</table>
-
 ## 🖥️ Hardware Configurations
 
 LocalAGI supports multiple hardware configurations through Docker Compose profiles:
@@ -110,7 +81,7 @@ LocalAGI supports multiple hardware configurations through Docker Compose profil
 - Uses CUDA for acceleration
 - Best for high-performance inference
 - Supports text, multimodal, and image generation models
-- Run with: `docker compose -f docker-compose.nvidia.yaml up`
+- Run with: `docker compose --profile nvidia up`
 - Default models:
   - Text: `arcee-agent`
   - Multimodal: `minicpm-v-2_6`
@@ -126,7 +97,7 @@ LocalAGI supports multiple hardware configurations through Docker Compose profil
 - Uses SYCL for acceleration
 - Best for Intel-based systems
 - Supports text, multimodal, and image generation models
-- Run with: `docker compose -f docker-compose.intel.yaml up`
+- Run with: `docker compose --profile intel up`
 - Default models:
   - Text: `arcee-agent`
   - Multimodal: `minicpm-v-2_6`
@@ -149,13 +120,13 @@ MODEL_NAME=gemma-3-12b-it docker compose up
 MODEL_NAME=gemma-3-12b-it \
 MULTIMODAL_MODEL=minicpm-v-2_6 \
 IMAGE_MODEL=flux.1-dev \
-docker compose -f docker-compose.nvidia.yaml up
+docker compose --profile nvidia up
 
 # Intel GPU with custom models
 MODEL_NAME=gemma-3-12b-it \
 MULTIMODAL_MODEL=minicpm-v-2_6 \
 IMAGE_MODEL=sd-1.5-ggml \
-docker compose -f docker-compose.intel.yaml up
+docker compose --profile intel up
 ```
 
 If no models are specified, it will use the defaults:

core/agent/agent_test.go

@@ -238,7 +238,7 @@ var _ = Describe("Agent test", func() {
 			defer agent.Stop()
 
 			result := agent.Ask(
-				types.WithText("Thoroughly plan a trip to San Francisco from Venice, Italy; check flight times, visa requirements and whether electrical items are allowed in cabin luggage."),
+				types.WithText("plan a trip to San Francisco from Venice, Italy"),
 			)
 			Expect(len(result.State)).To(BeNumerically(">", 1))
 
@@ -260,7 +260,6 @@ var _ = Describe("Agent test", func() {
 				WithLLMAPIURL(apiURL),
 				WithModel(testModel),
 				WithLLMAPIKey(apiKeyURL),
-				WithTimeout("10m"),
 				WithNewConversationSubscriber(func(m openai.ChatCompletionMessage) {
 					mu.Lock()
 					message = m

docker-compose.intel.yaml

@@ -1,33 +0,0 @@
-services:
-  localai:
-    extends:
-      file: docker-compose.yaml
-      service: localai
-    environment:
-      - LOCALAI_SINGLE_ACTIVE_BACKEND=true
-      - DEBUG=true
-    image: localai/localai:master-sycl-f32-ffmpeg-core
-    devices:
-      # On a system with integrated GPU and an Arc 770, this is the Arc 770
-      - /dev/dri/card1
-      - /dev/dri/renderD129
-    command: 
-    - ${MODEL_NAME:-arcee-agent}
-    - ${MULTIMODAL_MODEL:-minicpm-v-2_6}
-    - ${IMAGE_MODEL:-sd-1.5-ggml}
-    - granite-embedding-107m-multilingual
-
-  localrecall:
-    extends:
-      file: docker-compose.yaml
-      service: localrecall
-
-  localrecall-healthcheck:
-    extends:
-      file: docker-compose.yaml
-      service: localrecall-healthcheck
-
-  localagi:
-    extends:
-      file: docker-compose.yaml
-      service: localagi

docker-compose.nvidia.yaml

@@ -1,31 +0,0 @@
-services:
-  localai:
-    extends:
-      file: docker-compose.yaml
-      service: localai
-    environment:
-      - LOCALAI_SINGLE_ACTIVE_BACKEND=true
-      - DEBUG=true
-    image: localai/localai:master-sycl-f32-ffmpeg-core
-    deploy:
-      resources:
-        reservations:
-          devices:
-            - driver: nvidia
-              count: 1
-              capabilities: [gpu]
-
-  localrecall:
-    extends:
-      file: docker-compose.yaml
-      service: localrecall
-
-  localrecall-healthcheck:
-    extends:
-      file: docker-compose.yaml
-      service: localrecall-healthcheck
-
-  localagi:
-    extends:
-      file: docker-compose.yaml
-      service: localagi

docker-compose.yaml

@@ -7,9 +7,8 @@ services:
     # Image list (dockerhub): https://hub.docker.com/r/localai/localai
     image: localai/localai:master-ffmpeg-core
     command: 
+    # - gemma-3-12b-it
     - ${MODEL_NAME:-arcee-agent}
-    - ${MULTIMODAL_MODEL:-minicpm-v-2_6}
-    - ${IMAGE_MODEL:-flux.1-dev}
     - granite-embedding-107m-multilingual
     healthcheck:
       test: ["CMD", "curl", "-f", "http://localhost:8080/readyz"]
@@ -25,6 +24,44 @@ services:
       - ./volumes/models:/build/models:cached
       - ./volumes/images:/tmp/generated/images
 
+  localai-nvidia:
+    profiles: ["nvidia"]
+    extends:
+      service: localai
+    environment:
+      - LOCALAI_SINGLE_ACTIVE_BACKEND=true
+      - DEBUG=true
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: 1
+              capabilities: [gpu]
+    command: 
+    - ${MODEL_NAME:-arcee-agent}
+    - ${MULTIMODAL_MODEL:-minicpm-v-2_6}
+    - ${IMAGE_MODEL:-flux.1-dev}
+    - granite-embedding-107m-multilingual
+
+  localai-intel:
+    profiles: ["intel"]
+    environment:
+      - LOCALAI_SINGLE_ACTIVE_BACKEND=true
+      - DEBUG=true
+    extends:
+      service: localai
+    image: localai/localai:master-sycl-f32-ffmpeg-core
+    devices:
+      # On a system with integrated GPU and an Arc 770, this is the Arc 770
+      - /dev/dri/card1
+      - /dev/dri/renderD129
+    command: 
+    - ${MODEL_NAME:-arcee-agent}
+    - ${MULTIMODAL_MODEL:-minicpm-v-2_6}
+    - ${IMAGE_MODEL:-sd-1.5-ggml}
+    - granite-embedding-107m-multilingual
+
   localrecall:
     image: quay.io/mudler/localrecall:main
     ports:
@@ -60,8 +97,6 @@ services:
     #image: quay.io/mudler/localagi:master
     environment:
       - LOCALAGI_MODEL=${MODEL_NAME:-arcee-agent}
-      - LOCALAGI_MULTIMODAL_MODEL=${MULTIMODAL_MODEL:-minicpm-v-2_6}
-      - LOCALAGI_IMAGE_MODEL=${IMAGE_MODEL:-sd-1.5-ggml}
       - LOCALAGI_LLM_API_URL=http://localai:8080
       #- LOCALAGI_LLM_API_KEY=sk-1234567890
       - LOCALAGI_LOCALRAG_URL=http://localrecall:8080
@@ -71,4 +106,32 @@ services:
     extra_hosts:
       - "host.docker.internal:host-gateway"
     volumes:
-      - ./volumes/localagi/:/pool
+      - ./volumes/localagi/:/pool
+
+  localagi-nvidia:
+    profiles: ["nvidia"]
+    extends:
+      service: localagi
+    environment:
+      - LOCALAGI_MODEL=${MODEL_NAME:-arcee-agent}
+      - LOCALAGI_MULTIMODAL_MODEL=${MULTIMODAL_MODEL:-minicpm-v-2_6}
+      - LOCALAGI_IMAGE_MODEL=${IMAGE_MODEL:-flux.1-dev}
+      - LOCALAGI_LLM_API_URL=http://localai:8080
+      - LOCALAGI_LOCALRAG_URL=http://localrecall:8080
+      - LOCALAGI_STATE_DIR=/pool
+      - LOCALAGI_TIMEOUT=5m
+      - LOCALAGI_ENABLE_CONVERSATIONS_LOGGING=false
+
+  localagi-intel:
+    profiles: ["intel"]
+    extends:
+      service: localagi
+    environment:
+      - LOCALAGI_MODEL=${MODEL_NAME:-arcee-agent}
+      - LOCALAGI_MULTIMODAL_MODEL=${MULTIMODAL_MODEL:-minicpm-v-2_6}
+      - LOCALAGI_IMAGE_MODEL=${IMAGE_MODEL:-sd-1.5-ggml}
+      - LOCALAGI_LLM_API_URL=http://localai:8080
+      - LOCALAGI_LOCALRAG_URL=http://localrecall:8080
+      - LOCALAGI_STATE_DIR=/pool
+      - LOCALAGI_TIMEOUT=5m
+      - LOCALAGI_ENABLE_CONVERSATIONS_LOGGING=false