atlasbot: move to service image and add nats queue infra

clusters/atlas/flux-system/applications/comms/image-automation.yaml

@@ -0,0 +1,26 @@
+# clusters/atlas/flux-system/applications/comms/image-automation.yaml
+apiVersion: image.toolkit.fluxcd.io/v1
+kind: ImageUpdateAutomation
+metadata:
+  name: comms
+  namespace: comms
+spec:
+  interval: 1m0s
+  sourceRef:
+    kind: GitRepository
+    name: flux-system
+    namespace: flux-system
+  git:
+    checkout:
+      ref:
+        branch: feature/ariadne
+    commit:
+      author:
+        email: ops@bstein.dev
+        name: flux-bot
+      messageTemplate: "chore(comms): automated image update"
+    push:
+      branch: feature/ariadne
+  update:
+    strategy: Setters
+    path: services/comms

clusters/atlas/flux-system/applications/kustomization.yaml

@@ -6,6 +6,7 @@ resources:
   - vault/kustomization.yaml
   - vaultwarden/kustomization.yaml
   - comms/kustomization.yaml
+  - comms/image-automation.yaml
   - crypto/kustomization.yaml
   - monerod/kustomization.yaml
   - pegasus/kustomization.yaml

clusters/atlas/flux-system/platform/kustomization.yaml

@@ -16,5 +16,6 @@ resources:
   - longhorn/kustomization.yaml
   - longhorn-ui/kustomization.yaml
   - postgres/kustomization.yaml
+  - nats/kustomization.yaml
   - ../platform/vault-csi/kustomization.yaml
   - ../platform/vault-injector/kustomization.yaml

infrastructure/nats/configmap.yaml

@@ -0,0 +1,17 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: nats-config
+  namespace: nats
+  labels:
+    app: nats
+    component: config
+  annotations:
+    description: "NATS JetStream configuration"
+data:
+  nats.conf: |
+    jetstream {
+      store_dir: /data
+      max_mem_store: 128MB
+      max_file_store: 1GB
+    }

infrastructure/nats/kustomization.yaml

@@ -0,0 +1,7 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+resources:
+  - namespace.yaml
+  - configmap.yaml
+  - service.yaml
+  - statefulset.yaml

infrastructure/nats/namespace.yaml

@@ -0,0 +1,4 @@
+apiVersion: v1
+kind: Namespace
+metadata:
+  name: nats

infrastructure/nats/service.yaml

@@ -0,0 +1,17 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: nats
+  namespace: nats
+  labels:
+    app: nats
+spec:
+  selector:
+    app: nats
+  ports:
+    - name: client
+      port: 4222
+      targetPort: 4222
+    - name: monitoring
+      port: 8222
+      targetPort: 8222

infrastructure/nats/statefulset.yaml

@@ -0,0 +1,54 @@
+apiVersion: apps/v1
+kind: StatefulSet
+metadata:
+  name: nats
+  namespace: nats
+  labels:
+    app: nats
+spec:
+  serviceName: nats
+  replicas: 1
+  selector:
+    matchLabels:
+      app: nats
+  template:
+    metadata:
+      labels:
+        app: nats
+    spec:
+      containers:
+        - name: nats
+          image: nats:2.10.18
+          args:
+            - "-c"
+            - "/etc/nats/nats.conf"
+          ports:
+            - name: client
+              containerPort: 4222
+            - name: monitoring
+              containerPort: 8222
+          volumeMounts:
+            - name: config
+              mountPath: /etc/nats
+            - name: data
+              mountPath: /data
+          resources:
+            requests:
+              cpu: 100m
+              memory: 256Mi
+            limits:
+              cpu: 500m
+              memory: 512Mi
+      volumes:
+        - name: config
+          configMap:
+            name: nats-config
+  volumeClaimTemplates:
+    - metadata:
+        name: data
+      spec:
+        accessModes:
+          - ReadWriteOnce
+        resources:
+          requests:
+            storage: 2Gi

services/comms/atlasbot-deployment.yaml

@@ -58,12 +58,12 @@ spec:
         hardware: rpi5
       containers:
         - name: atlasbot
-          image: python:3.11-slim
+          image: registry.bstein.dev/bstein/atlasbot:0.1.0-0
           command: ["/bin/sh","-c"]
           args:
             - |
               . /vault/scripts/comms_vault_env.sh
-              exec python /app/bot.py
+              exec python -m atlasbot.main
           env:
             - name: MATRIX_BASE
               value: http://othrys-synapse-matrix-synapse:8008
@@ -78,25 +78,41 @@ spec:
             - name: BOT_USER
               value: atlasbot
             - name: BOT_MENTIONS
-              value: atlasbot,aatlasbot,atlas_quick,atlas_smart
+              value: atlasbot,aatlasbot,atlas-quick,atlas-smart
             - name: OLLAMA_URL
               value: http://ollama.ai.svc.cluster.local:11434
             - name: OLLAMA_MODEL
               value: qwen2.5:14b-instruct
             - name: ATLASBOT_MODEL_FAST
               value: qwen2.5:14b-instruct-q4_0
-            - name: ATLASBOT_MODEL_DEEP
+            - name: ATLASBOT_MODEL_SMART
               value: qwen2.5:14b-instruct
             - name: OLLAMA_FALLBACK_MODEL
               value: qwen2.5:14b-instruct-q4_0
             - name: OLLAMA_TIMEOUT_SEC
               value: "600"
             - name: ATLASBOT_THINKING_INTERVAL_SEC
-              value: "120"
+              value: "30"
             - name: ATLASBOT_SNAPSHOT_TTL_SEC
               value: "30"
             - name: ATLASBOT_HTTP_PORT
               value: "8090"
+            - name: ATLASBOT_QUEUE_ENABLED
+              value: "true"
+            - name: ATLASBOT_NATS_URL
+              value: nats://nats.nats.svc.cluster.local:4222
+            - name: ATLASBOT_NATS_STREAM
+              value: atlasbot
+            - name: ATLASBOT_NATS_SUBJECT
+              value: atlasbot.requests
+            - name: ATLASBOT_FAST_MAX_ANGLES
+              value: "2"
+            - name: ATLASBOT_SMART_MAX_ANGLES
+              value: "5"
+            - name: ATLASBOT_FAST_MAX_CANDIDATES
+              value: "2"
+            - name: ATLASBOT_SMART_MAX_CANDIDATES
+              value: "6"
           ports:
             - name: http
               containerPort: 8090
@@ -108,9 +124,6 @@ spec:
               cpu: 500m
               memory: 512Mi
           volumeMounts:
-            - name: code
-              mountPath: /app/bot.py
-              subPath: bot.py
             - name: kb
               mountPath: /kb
               readOnly: true
@@ -118,9 +131,6 @@ spec:
               mountPath: /vault/scripts
               readOnly: true
       volumes:
-        - name: code
-          configMap:
-            name: atlasbot
         - name: kb
           configMap:
             name: atlas-kb

services/comms/image.yaml

@@ -0,0 +1,23 @@
+# services/comms/image.yaml
+apiVersion: image.toolkit.fluxcd.io/v1beta2
+kind: ImageRepository
+metadata:
+  name: atlasbot
+  namespace: comms
+spec:
+  image: registry.bstein.dev/bstein/atlasbot
+  interval: 1m0s
+  secretRef:
+    name: harbor-regcred
+---
+apiVersion: image.toolkit.fluxcd.io/v1beta2
+kind: ImagePolicy
+metadata:
+  name: atlasbot
+  namespace: comms
+spec:
+  imageRepositoryRef:
+    name: atlasbot
+  policy:
+    semver:
+      range: ">=0.1.0-0"

services/comms/kustomization.yaml

@@ -4,6 +4,7 @@ kind: Kustomization
 namespace: comms
 resources:
   - namespace.yaml
+  - image.yaml
   - serviceaccount.yaml
   - secretproviderclass.yaml
   - mas-configmap.yaml
@@ -44,6 +45,10 @@ resources:
   - livekit-middlewares.yaml
   - matrix-ingress.yaml
 
+images:
+  - name: registry.bstein.dev/bstein/atlasbot
+    newTag: 0.1.0-0 # {"$imagepolicy": "comms:atlasbot:tag"}
+
 configMapGenerator:
   - name: comms-vault-env
     files:
@@ -60,11 +65,6 @@ configMapGenerator:
       - server.py=scripts/guest-register/server.py
     options:
       disableNameSuffixHash: true
-  - name: atlasbot
-    files:
-      - bot.py=scripts/atlasbot/bot.py
-    options:
-      disableNameSuffixHash: true
   - name: othrys-element-host-config
     files:
       - 20-host-config.sh=scripts/element-host-config.sh