remove qwen 3.5 4b and disable thinking in agent crons

home-manager/configmap.yaml

@@ -82,6 +82,14 @@ data:
     the home comfortable, safe, and efficient by talking to Home Assistant, and
     to notify your owner (Roger) on Discord when something needs a human.
 
+    ## Response speed
+
+    Do not use extended thinking or produce a hidden reasoning process for this
+    agent. Answer directly and concisely, using only the reasoning needed to
+    safely complete the request. Never include a chain of thought or a
+    `reasoning_content` section in the response. This is a prompt-level
+    instruction; do not change the llama.cpp server configuration.
+
     ## The home you look after
 
     - **Home Assistant:** the brain of the home. Runs in namespace

litellm/litellm.yaml

@@ -52,12 +52,6 @@ data:
           model: openai/qwen3.6-27b
           api_base: http://llamacpp-qwen36-27b.llamacpp/v1
           api_key: "sk-no-auth"
-      # Small, fast model intended for Home Assistant voice Assist.
-      - model_name: qwen3.5-4b
-        litellm_params:
-          model: openai/qwen3.5-4b
-          api_base: http://llamacpp-qwen35-4b.llamacpp/v1
-          api_key: "sk-no-auth"
     router_settings:
       fallbacks:
         - deepseek-v4-flash-0731: [qwen3.6-27b]

llamacpp/README.md

@@ -15,7 +15,6 @@ to the NUCBox (`nodeSelector: {kubernetes.io/arch: amd64, hardware: high-memory}
 | Alias                    | Model                          | GGUF                                                  | Service                                              | Args ref |
 |--------------------------|--------------------------------|-------------------------------------------------------|------------------------------------------------------|----------|
 | `deepseek-v4-flash-0731` | DeepSeek-V4-Flash-0731 (MoE)   | unsloth/DeepSeek-V4-Flash-0731-GGUF (UD-IQ1_M, ~87 GiB) | `llamacpp-deepseek-v4-flash-0731.llamacpp:80`        | [args-deepseek-v4-flash-0731.md](args-deepseek-v4-flash-0731.md) |
-| `qwen3.5-4b`             | Qwen3.5-4B (MTP)              | unsloth/Qwen3.5-4B-MTP-GGUF (`UD-Q4_K_XL`)           | `llamacpp-qwen35-4b.llamacpp:80`                    | — |
 
 DeepSeek-V4-Flash-0731 is a Mixture-of-Experts model (256 experts, 6 active per
 token) with MLA attention, so only a small fraction of the weights is computed
@@ -151,8 +150,3 @@ to VRAM).
    directory recursively.)
 4. Check the VRAM budget table above — at ~87 GiB this model nearly fills the
    90 GiB pool on its own, so co-locating another large model is not possible.
-
-The `qwen3.5-4b` alias is exposed through LiteLLM as a low-latency option for
-Home Assistant voice Assist. Select this model in the Home Assistant
-conversation/voice Assist provider configuration; the LiteLLM endpoint is
-`http://litellm-service.litellm:80/v1` from inside the cluster.

llamacpp/deployment-qwen35-4b.yaml

@@ -1,138 +0,0 @@
-# Qwen3.5-4B (MTP, UD-Q4_K_XL) served by llama.cpp for low-latency assistants.
-# The model is fully offloaded to the NUCBox Radeon 8060S. Model weights are
-# stored on the shared llamacpp-models hostPath PVC.
----
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  name: llamacpp-qwen35-4b
-  namespace: llamacpp
-  labels:
-    app: llamacpp
-    model: qwen3.5-4b
-spec:
-  replicas: 1
-  strategy:
-    type: Recreate
-  selector:
-    matchLabels:
-      app: llamacpp
-      model: qwen3.5-4b
-  template:
-    metadata:
-      labels:
-        app: llamacpp
-        model: qwen3.5-4b
-    spec:
-      nodeSelector:
-        kubernetes.io/arch: amd64
-        hardware: high-memory
-      initContainers:
-      - name: fetch-model
-        image: alpine:3.20
-        command: ["/bin/sh", "-c"]
-        args:
-        - |
-          set -e
-          if [ -s "/models/$MODEL_FILE" ]; then
-            echo "Model $MODEL_FILE already present — skipping download."
-            exit 0
-          fi
-          apk add --no-cache curl
-          echo "Downloading $MODEL_FILE from $MODEL_URL ..."
-          curl -fL --retry 5 --retry-delay 5 -o "/models/$MODEL_FILE.partial" "$MODEL_URL"
-          mv "/models/$MODEL_FILE.partial" "/models/$MODEL_FILE"
-          echo "Download complete: $(ls -lh /models/$MODEL_FILE)"
-        env:
-        - name: MODEL_URL
-          value: "https://huggingface.co/unsloth/Qwen3.5-4B-MTP-GGUF/resolve/main/Qwen3.5-4B-UD-Q4_K_XL.gguf"
-        - name: MODEL_FILE
-          value: "Qwen3.5-4B-UD-Q4_K_XL.gguf"
-        volumeMounts:
-        - name: models
-          mountPath: /models
-      containers:
-      - name: llama-server
-        image: ghcr.io/ggml-org/llama.cpp:server-vulkan
-        imagePullPolicy: IfNotPresent
-        args:
-        - -m
-        - /models/Qwen3.5-4B-UD-Q4_K_XL.gguf
-        - --alias
-        - qwen3.5-4b
-        - --host
-        - 0.0.0.0
-        - --port
-        - "8080"
-        - --jinja
-        - -ngl
-        - "999"
-        - -c
-        - "65536"
-        - -np
-        - "1"
-        - --cont-batching
-        - --cache-type-k
-        - q8_0
-        - --cache-type-v
-        - q8_0
-        - --threads
-        - "8"
-        ports:
-        - name: http
-          containerPort: 8080
-        resources:
-          requests:
-            cpu: "1000m"
-            memory: 2Gi
-          limits:
-            cpu: "4000m"
-            memory: 8Gi
-        readinessProbe:
-          httpGet:
-            path: /health
-            port: 8080
-          initialDelaySeconds: 30
-          periodSeconds: 10
-          failureThreshold: 6
-        livenessProbe:
-          httpGet:
-            path: /health
-            port: 8080
-          initialDelaySeconds: 120
-          periodSeconds: 30
-          failureThreshold: 5
-        securityContext:
-          privileged: true
-        volumeMounts:
-        - name: models
-          mountPath: /models
-          readOnly: true
-        - name: dri
-          mountPath: /dev/dri
-      volumes:
-      - name: models
-        persistentVolumeClaim:
-          claimName: llamacpp-models
-      - name: dri
-        hostPath:
-          path: /dev/dri
-          type: Directory
----
-apiVersion: v1
-kind: Service
-metadata:
-  name: llamacpp-qwen35-4b
-  namespace: llamacpp
-  labels:
-    app: llamacpp
-    model: qwen3.5-4b
-spec:
-  type: ClusterIP
-  selector:
-    app: llamacpp
-    model: qwen3.5-4b
-  ports:
-  - name: http
-    port: 80
-    targetPort: 8080

platform-engineer/configmap.yaml

@@ -85,6 +85,14 @@ data:
     to keep it healthy, fix small problems before they grow, and notify your
     owner (Roger) on Discord when something needs a human.
 
+    ## Response speed
+
+    Do not use extended thinking or produce a hidden reasoning process for this
+    agent. Answer directly and concisely, using only the reasoning needed to
+    safely complete the request. Never include a chain of thought or a
+    `reasoning_content` section in the response. This is a prompt-level
+    instruction; do not change the llama.cpp server configuration.
+
     ## The cluster you look after
 
     - **Nodes:** `raspberrypi` (control-plane, arm64, 4 GiB), `rpi2` (arm,