feat: poimen-toolkit ArgoCD app + sourceRepo

- k8s/argocd/apps/71-poimen-toolkit.yaml: Application wave-7, points to
  poimen-toolkit repo k8s/ path, ServerSideApply for CRD schema size,
  image-updater for controller:latest digest
- k8s/argocd/projects/homelab-project.yaml: add poimen-toolkit.git to sourceRepos

k8s/apps/paperless/paperless-ai-new.yaml

@@ -0,0 +1,127 @@
+apiVersion: v1
+kind: PersistentVolumeClaim
+metadata:
+  name: paperless-ai-data
+  namespace: paperless
+spec:
+  accessModes:
+    - ReadWriteOnce
+  storageClassName: longhorn
+  resources:
+    requests:
+      storage: 2Gi
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: paperless-ai
+  namespace: paperless
+  labels:
+    app.kubernetes.io/name: paperless-ai
+spec:
+  replicas: 1
+  selector:
+    matchLabels:
+      app.kubernetes.io/name: paperless-ai
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/name: paperless-ai
+    spec:
+      tolerations:
+        - key: node-role.kubernetes.io/control-plane
+          operator: Exists
+          effect: NoSchedule
+      
+      volumes:
+        - name: paperless-ai-data
+          persistentVolumeClaim:
+            claimName: paperless-ai-data
+      
+      initContainers:
+        - name: fetch-llm-token
+          image: curlimages/curl:8.12.0
+          command:
+            - sh
+            - -c
+            - |
+              set -e
+              echo "[init] Fetching JWT token from Authentik for paperless-ai-agent..."
+              
+              # Get JWT token via client_credentials grant
+              TOKEN_RESPONSE=$(curl -s -X POST https://authentik.riotpiao.com/application/o/token/ \
+                -d "grant_type=client_credentials" \
+                -d "client_id=paperless-ai-agent" \
+                -d "client_secret=29skAhE0tBzWn0qrPvmPTQMva0joFjcCr7msDQr_VXQ" \
+                -d "scope=openid llm:inference" 2>/dev/null)
+              
+              # Extract token
+              TOKEN=$(echo "$TOKEN_RESPONSE" | grep -o '"access_token":"[^"]*' | cut -d'"' -f4)
+              
+              if [ -z "$TOKEN" ]; then
+                echo "[error] Failed to get token. Response: $TOKEN_RESPONSE"
+                exit 1
+              fi
+              
+              # Store token in file for main container to read
+              mkdir -p /data
+              echo "$TOKEN" > /data/llm_token.txt
+              echo "[init] Token fetched and stored successfully"
+          volumeMounts:
+            - name: paperless-ai-data
+              mountPath: /data
+      
+      containers:
+        - name: paperless-ai
+          image: clusterzx/paperless-ai:latest
+          imagePullPolicy: Always
+          env:
+            # Paperless-ngx connection
+            - name: PAPERLESS_API_URL
+              value: "http://paperless.paperless.svc.cluster.local:8000"
+            - name: PAPERLESS_API_TOKEN
+              valueFrom:
+                secretKeyRef:
+                  name: paperless-ai-config
+                  key: PAPERLESS_API_TOKEN
+            - name: PAPERLESS_USERNAME
+              value: "admin"
+            
+            # LLM API configuration
+            - name: AI_PROVIDER
+              value: "custom"
+            - name: CUSTOM_BASE_URL
+              value: "https://api.riotpiao.com/v1"
+            # Token file created by init container with JWT from Authentik
+            - name: CUSTOM_API_KEY_FILE
+              value: "/app/data/llm_token.txt"
+            - name: CUSTOM_MODEL
+              value: "qwen2.5:3b-instruct"
+            
+            # Scanning behavior
+            - name: SCAN_INTERVAL
+              value: "60"
+            - name: PROCESS_PREDEFINED_DOCUMENTS
+              value: "no"
+            
+            # Tagging configuration
+            - name: ADD_AI_TAG
+              value: "yes"
+            - name: AI_TAG_NAME
+              value: "ai-processed"
+            - name: ADD_AI_DESCRIPTIONS
+              value: "yes"
+            - name: USE_PROMPT_TAGS
+              value: "yes"
+          
+          volumeMounts:
+            - name: paperless-ai-data
+              mountPath: /app/data
+          
+          resources:
+            requests:
+              cpu: 100m
+              memory: 512Mi
+            limits:
+              cpu: "1"
+              memory: 2Gi

k8s/argocd/apps/71-poimen-toolkit.yaml

@@ -0,0 +1,34 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Application
+metadata:
+  name: poimen-toolkit
+  namespace: argocd
+  annotations:
+    argocd.argoproj.io/sync-wave: "7"
+    argocd-image-updater.argoproj.io/image-list: |
+      controller=ghcr.io/riotpiao-poimen/poimen-toolkit-controller
+    argocd-image-updater.argoproj.io/controller.update-strategy: digest
+    argocd-image-updater.argoproj.io/controller.allow-tags: regexp:^latest$
+    argocd-image-updater.argoproj.io/write-back-method: argocd
+spec:
+  project: homelab
+  source:
+    repoURL: https://forgejo.riotpiao.com/riotpiao-poimen/poimen-toolkit.git
+    targetRevision: main
+    path: k8s
+  destination:
+    server: https://kubernetes.default.svc
+    namespace: poimen
+  syncPolicy:
+    automated:
+      prune: true
+      selfHeal: true
+    syncOptions:
+      - CreateNamespace=true
+      - ServerSideApply=true
+    retry:
+      limit: 5
+      backoff:
+        duration: 5s
+        factor: 2
+        maxDuration: 3m

k8s/argocd/projects/homelab-project.yaml

@@ -24,6 +24,7 @@ spec:
     - https://forgejo.riotpiao.com/riotpiao-poimen/poimen-memory.git
     - https://forgejo.riotpiao.com/riotpiao-poimen/poimen-workflows.git
     - https://forgejo.riotpiao.com/riotpiao-poimen/poimen-frontend.git
+    - https://forgejo.riotpiao.com/riotpiao-poimen/poimen-toolkit.git
     - https://forgejo.riotpiao.com/rock/riotpiao.com.git
     # Public Helm chart repos referenced by k8s/argocd/apps/* and bootstrap/*
     - https://cloudnative-pg.github.io/charts

scripts/iam/provision-rbac.py

@@ -145,6 +145,7 @@ SERVICE_ACCOUNTS: Dict[str, Dict[str, Any]] = {
 SCOPE_MAPPINGS: Dict[str, Dict[str, str]] = {
     "roles": {"expression": 'return user.attributes.get("roles", [])'},
     "permissions": {"expression": 'return ["*"] if any(user.groups.filter(is_superuser=True)) else list(user.groups.values_list("name", flat=True))'},
+    "groups": {"expression": 'return {"groups": list(user.groups.values_list("name", flat=True))}'},
     "minio_buckets": {"expression": 'return user.attributes.get("minio_buckets", [])'},
     "paperless_doctypes": {"expression": 'return user.attributes.get("paperless_doctypes", [])'},
     "memory_projects": {"expression": 'return user.attributes.get("memory_projects", [])'},
@@ -246,6 +247,25 @@ for scope_name, scope_spec in SCOPE_MAPPINGS.items():
         else:
             print(f"  {scope_name}: FAILED {status} {res}")
 
+# Fix built-in 'openid' scope to include preferred_username (needed by Grafana, Forgejo, etc.)
+# Note: sub MUST be a string, not int, for JSON compatibility with Go struct unmarshaling
+if "openid" in existing_scopes:
+    openid_scope = existing_scopes["openid"]
+    openid_pk = openid_scope["pk"]
+    openid_expression = 'return {"sub": str(user.pk), "preferred_username": user.username}'
+    if openid_expression not in openid_scope.get("expression", ""):
+        status, res = api("PUT", f"/api/v3/propertymappings/provider/scope/{openid_pk}/", {
+            "name": openid_scope["name"],
+            "scope_name": "openid",
+            "expression": openid_expression,
+        })
+        if status in (200, 201):
+            print(f"  openid: updated (sub as string + preferred_username)")
+        else:
+            print(f"  openid: UPDATE FAILED {status} {res}")
+    else:
+        print(f"  openid: already correct (sub as string)")
+
 # ===========================================================================
 # Phase 4: Get flow UUIDs (needed for providers)
 # ===========================================================================