chore: cleanup, identify goal from conversation when evaluting achievement (#29)

* chore: cleanup, identify goal from conversation when evaluting achievement

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

* change base cpu model

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

* this is not necessary anymore

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

* use 12b

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

* use openthinker, it's smaller

* chore(tests): set timeout

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

* Enable reasoning in some of the tests

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

* docker compose unification, small changes

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

* Simplify

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

* Back at arcee-agent as default

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

* Better error handling during planning

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

* Ci: do not run jobs for every branch

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

---------

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

docker-compose.yaml

@@ -7,7 +7,8 @@ services:
     # Image list (dockerhub): https://hub.docker.com/r/localai/localai
     image: localai/localai:master-ffmpeg-core
     command: 
-    - arcee-agent # (smaller)
+    # - gemma-3-12b-it
+    - ${MODEL_NAME:-arcee-agent}
     - granite-embedding-107m-multilingual
     healthcheck:
       test: ["CMD", "curl", "-f", "http://localhost:8080/readyz"]
@@ -23,14 +24,44 @@ services:
       - ./volumes/models:/build/models:cached
       - ./volumes/images:/tmp/generated/images
 
-    # decomment the following piece if running with Nvidia GPUs
-    # deploy:
-    #   resources:
-    #     reservations:
-    #       devices:
-    #         - driver: nvidia
-    #           count: 1
-    #           capabilities: [gpu]
+  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}
+    - ${IMAGE_MODEL:-sd-1.5-ggml}
+    - granite-embedding-107m-multilingual
+
   localrecall:
     image: quay.io/mudler/localrecall:main
     ports:
@@ -65,7 +96,7 @@ services:
       - 8080:3000
     #image: quay.io/mudler/localagi:master
     environment:
-      - LOCALAGI_MODEL=arcee-agent
+      - LOCALAGI_MODEL=${MODEL_NAME:-arcee-agent}
       - LOCALAGI_LLM_API_URL=http://localai:8080
       #- LOCALAGI_LLM_API_KEY=sk-1234567890
       - LOCALAGI_LOCALRAG_URL=http://localrecall:8080
@@ -76,3 +107,31 @@ services:
       - "host.docker.internal:host-gateway"
     volumes:
       - ./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