buun-stack/jupyterhub/jupyterhub-values.gomplate.yaml

hub:
  extraEnv:
    JUPYTERHUB_CRYPT_KEY: {{ .Env.JUPYTERHUB_CRYPT_KEY | quote }}

  # Install packages at container startup
  extraFiles:
    startup.sh:
      mountPath: /usr/local/bin/startup.sh
      mode: 0755
      stringData: |
        #!/bin/bash
        pip install --no-cache-dir hvac==2.3.0
        exec jupyterhub --config /usr/local/etc/jupyterhub/jupyterhub_config.py --upgrade-db
    user_policy.hcl:
      mountPath: /srv/jupyterhub/user_policy.hcl
      mode: 0644
      stringData: |
{{ .Env.USER_POLICY_HCL | strings.Indent 8 }}

  # Override the default command to run our startup script first
  command:
    - /usr/local/bin/startup.sh

  config:
    JupyterHub:
      authenticator_class: generic-oauth
      admin_access: false

    Authenticator:
      enable_auth_state: true
      allow_all: true # allow all Keycloak users

    GenericOAuthenticator:
      client_id: {{ .Env.JUPYTERHUB_OIDC_CLIENT_ID }}
      oauth_callback_url: "https://{{ .Env.JUPYTERHUB_HOST }}/hub/oauth_callback"
      authorize_url: "https://{{ .Env.KEYCLOAK_HOST }}/realms/{{ .Env.KEYCLOAK_REALM }}/protocol/openid-connect/auth"
      token_url: "https://{{ .Env.KEYCLOAK_HOST }}/realms/{{ .Env.KEYCLOAK_REALM }}/protocol/openid-connect/token"
      userdata_url: "https://{{ .Env.KEYCLOAK_HOST }}/realms/{{ .Env.KEYCLOAK_REALM }}/protocol/openid-connect/userinfo"
      login_service: keycloak
      # username_claim: email
      username_claim: preferred_username
      auth_refresh_age: 300  # Refresh auth token every 5 minutes
      refresh_pre_spawn: true  # Refresh token before spawning server

    OAuthenticator:
      scope:
        - openid
        - profile
        - email

  extraConfig:
    pre-spawn-hook: |
      # Set environment variables for spawned containers
      import hvac

      async def pre_spawn_hook(spawner):
          """Set essential environment variables for spawned containers"""
          # PostgreSQL configuration
          spawner.environment["POSTGRES_HOST"] = "postgres-cluster-rw.postgres"
          spawner.environment["POSTGRES_PORT"] = "5432"

          # JupyterHub API configuration
          spawner.environment["JUPYTERHUB_API_URL"] = "http://hub:8081/hub/api"

          # Logging configuration
          spawner.environment["BUUNSTACK_LOG_LEVEL"] = "{{ .Env.JUPYTER_BUUNSTACK_LOG_LEVEL }}"

          # Create user-specific Vault token directly
          try:
              username = spawner.user.name

              # Step 1: Initialize admin Vault client
              vault_client = hvac.Client(url="{{ .Env.VAULT_ADDR }}", verify=False)
              vault_client.token = "{{ .Env.JUPYTERHUB_VAULT_TOKEN }}"

              if not vault_client.is_authenticated():
                  raise Exception("Admin token is not authenticated")

              # Step 2: Create user-specific policy
              user_policy_name = "jupyter-user-{}".format(username)

              # Read policy template from file
              import os
              policy_template_path = "/srv/jupyterhub/user_policy.hcl"
              with open(policy_template_path, 'r') as f:
                  policy_template = f.read()

              # Replace {username} placeholder with actual username
              user_policy = policy_template.replace("{username}", username)

              # Write user-specific policy
              try:
                  vault_client.sys.create_or_update_policy(user_policy_name, user_policy)
                  spawner.log.info("✅ Created policy: {}".format(user_policy_name))
              except Exception as policy_e:
                  spawner.log.warning("Policy creation failed (may already exist): {}".format(policy_e))

              # Step 3: Create user-specific token
              token_response = vault_client.auth.token.create(
                  policies=[user_policy_name],
                  ttl="1h",
                  renewable=True,
                  display_name="notebook-{}".format(username)
              )

              user_vault_token = token_response["auth"]["client_token"]
              lease_duration = token_response["auth"].get("lease_duration", 3600)

              # Set user-specific Vault token as environment variable
              spawner.environment["NOTEBOOK_VAULT_TOKEN"] = user_vault_token

              spawner.log.info("✅ User-specific Vault token created for {} (expires in {}s, renewable)".format(username, lease_duration))

          except Exception as e:
              spawner.log.error("Failed to create user-specific Vault token for {}: {}".format(spawner.user.name, e))
              import traceback
              spawner.log.error("Full traceback: {}".format(traceback.format_exc()))

      c.KubeSpawner.pre_spawn_hook = pre_spawn_hook


  podSecurityContext:
    fsGroup: {{ .Env.JUPYTER_FSGID }}

singleuser:
  storage:
    {{ if env.Getenv "PVC_NAME" -}}
    type: static
    static:
      pvcName: {{ .Env.PVC_NAME }}
    {{ else -}}
    type: dynamic
    dynamic:
      {{ if env.Getenv "JUPYTERHUB_STORAGE_CLASS" -}}
      storageClass: {{ .Env.JUPYTERHUB_STORAGE_CLASS }}
      {{ end -}}
      storageAccessModes:
        - ReadWriteOnce
    {{ end -}}
    capacity: 10Gi

  extraEnv:
    VAULT_ADDR: "{{ .Env.VAULT_ADDR }}"

  networkPolicy:
    egress:
      - to:
          - namespaceSelector:
              matchLabels:
                kubernetes.io/metadata.name: postgres
        ports:
          - port: 5432
            protocol: TCP
      - to:
          - namespaceSelector:
              matchLabels:
                kubernetes.io/metadata.name: chroma
        ports:
          - port: 8000
            protocol: TCP
      - to:
          - namespaceSelector:
              matchLabels:
                kubernetes.io/metadata.name: qdrant
        ports:
          - port: 6333
            protocol: TCP
          - port: 6334
            protocol: TCP
          - port: 6335
            protocol: TCP
      - to:
          - namespaceSelector:
              matchLabels:
                kubernetes.io/metadata.name: litellm
        ports:
          - port: 4000
            protocol: TCP
      - to:
          - namespaceSelector:
              matchLabels:
                kubernetes.io/metadata.name: vault
        ports:
          - port: 8200
            protocol: TCP
      # Allow DNS resolution
      - to:
        - ipBlock:
            cidr: 0.0.0.0/0
        ports:
          - port: 53
            protocol: UDP
          - port: 53
            protocol: TCP
      # Allow HTTP traffic
      - to:
        - ipBlock:
            cidr: 0.0.0.0/0
        ports:
          - port: 80
            protocol: TCP
      # Allow HTTPS traffic
      - to:
        - ipBlock:
            cidr: 0.0.0.0/0
        ports:
          - port: 443
            protocol: TCP

  image:
    pullPolicy: IfNotPresent

  profileList:
    # https://quay.io/repository/jupyter/pyspark-notebook
    {{- if eq .Env.JUPYTER_PROFILE_MINIMAL_ENABLED "true" }}
    - display_name: "Minimal Jupyter Notebook Stack"
      description: "Minimal Jupyter Notebook Stack"
      kubespawner_override:
        image: quay.io/jupyter/minimal-notebook
    {{- end }}
    {{ if eq .Env.JUPYTER_PROFILE_BASE_ENABLED "true" }}
    - display_name: "Base Jupyter Notebook Stack"
      description: "Base Jupyter Notebook Stack"
      kubespawner_override:
        image: quay.io/jupyter/base-notebook
    {{- end }}
    {{- if eq .Env.JUPYTER_PROFILE_DATASCIENCE_ENABLED "true" }}
    - display_name: "Jupyter Notebook Data Science Stack"
      description: "Jupyter Notebook Data Science Stack"
      kubespawner_override:
        image: quay.io/jupyter/datascience-notebook
    {{- end }}
    {{- if eq .Env.JUPYTER_PROFILE_PYSPARK_ENABLED "true" }}
    - display_name: "Jupyter Notebook Python, Spark Stack"
      description: "Jupyter Notebook Python, Spark Stack"
      kubespawner_override:
        image: quay.io/jupyter/pyspark-notebook
    {{- end }}
    {{- if eq .Env.JUPYTER_PROFILE_PYTORCH_ENABLED "true" }}
    - display_name: "Jupyter Notebook PyTorch Deep Learning Stack"
      description: "Jupyter Notebook PyTorch Deep Learning Stack"
      kubespawner_override:
        image: quay.io/jupyter/pytorch-notebook
    {{- end }}
    {{- if eq .Env.JUPYTER_PROFILE_TENSORFLOW_ENABLED "true" }}
    - display_name: "Jupyter Notebook TensorFlow Deep Learning Stack"
      description: "Jupyter Notebook TensorFlow Deep Learning Stack"
      kubespawner_override:
        image: quay.io/jupyter/tensorflow-notebook
    {{- end }}
    {{- if eq .Env.JUPYTER_PROFILE_BUUN_STACK_ENABLED "true" }}
    - display_name: "Buun-stack"
      description: "Jupyter Notebook with buun-stack"
      kubespawner_override:
        image: "{{ .Env.IMAGE_REGISTRY }}/{{ .Env.KERNEL_IMAGE_BUUN_STACK_REPOSITORY }}:{{ .Env.JUPYTER_PYTHON_KERNEL_TAG }}"
    {{- end }}
    {{- if eq .Env.JUPYTER_PROFILE_BUUN_STACK_CUDA_ENABLED "true" }}
    - display_name: "Buun-stack with CUDA"
      description: "Jupyter Notebook with buun-stack and CUDA support"
      kubespawner_override:
        image: "{{ .Env.IMAGE_REGISTRY }}/{{ .Env.KERNEL_IMAGE_BUUN_STACK_CUDA_REPOSITORY }}:{{ .Env.JUPYTER_PYTHON_KERNEL_TAG }}"
        # resources:
        #   requests:
        #     nvidia.com/gpu: "1"
    {{- end }}

cull:
  enabled: true
  timeout: 7200      # 2 hours idle timeout
  every: 600         # Check every 10 minutes
  adminUsers: true   # Also cull admin users' server pods
  users: false       # Don't delete user accounts, only stop server pods

imagePullSecrets:
  - name: regcred

ingress:
  enabled: true
  annotations:
    kubernetes.io/ingress.class: traefik
    traefik.ingress.kubernetes.io/router.entrypoints: websecure
  ingressClassName: traefik
  hosts:
    - {{ .Env.JUPYTERHUB_HOST }}
  pathType: Prefix
  tls:
    - hosts:
        - {{ .Env.JUPYTERHUB_HOST }}