[jamesbxwu]

Context

Agentbricks has its own CLI today for building and deploying custom agents. We have plans to merge that into Databricks CLI once things are more stable but in the meantime, we are seeing reports where customers/agents are getting confused on how to use it. As a short term fix, we are updating the help section to point users to the agentbricks CLI.

Changes

Add custom-agents to the Agent Bricks help section, directing users to the standalone databricks-agentbricks package on PyPI. Invoking databricks custom-agents also displays the guidance. Update the help snapshot and add a release note.

Output from databricks -h using the updated CLI (Agent Bricks section):

Agent Bricks
  agent-kit                              *Beta* APIs for managing agent memory and durable session state.
  custom-agents                          *Beta* Please use the standalone databricks-agentbricks CLI on PyPi to build and deploy custom agents on databricks
  knowledge-assistants                   *Beta* Manage legacy Knowledge Assistants and related resources.
  supervisor-agents                      *Beta* Manage legacy Supervisor Agents and related resources.

Full databricks -h output

Databricks CLI

Usage:
  databricks [command]

Databricks Workspace
  fs                                     Filesystem related commands
  git-credentials                        Registers personal access token for Databricks to do operations on behalf of the user.
  repos                                  The Repos API allows users to manage their git repos.
  secrets                                The Secrets API allows you to manage secrets, secret scopes, and access permissions.
  workspace                              The Workspace API allows you to list, import, export, and delete workspace objects such as notebooks, files, folders, and dashboards.

Compute
  cluster-policies                       You can use cluster policies to control users' ability to configure clusters based on a set of rules.
  clusters                               The Clusters API allows you to create, start, edit, list, terminate, and delete clusters.
  global-init-scripts                    The Global Init Scripts API enables Workspace administrators to configure global initialization scripts for their workspace.
  instance-pools                         Instance Pools API are used to create, edit, delete and list instance pools by using ready-to-use cloud instances which reduces a cluster start and auto-scaling times.
  instance-profiles                      The Instance Profiles API allows admins to add, list, and remove instance profiles that users can launch clusters with.
  libraries                              The Libraries API allows you to install and uninstall libraries and get the status of libraries on a cluster.
  policy-compliance-for-clusters         The policy compliance APIs allow you to view and manage the policy compliance status of clusters in your workspace.
  policy-families                        View available policy families.

Sandbox
  sandbox                                *Beta* Create, manage, and control the lifecycle of sandboxes -- isolated, pre-configured, low-latency Serverless compute environments for running code.

Lakeflow
  jobs                                   The Jobs API allows you to create, edit, and delete jobs.
  pipelines                              The Lakeflow Spark Declarative Pipelines API allows you to create, edit, delete, start, and view details about pipelines.
  policy-compliance-for-jobs             The compliance APIs allow you to view and manage the policy compliance status of jobs in your workspace.

Machine Learning
  experiments                            Experiments are the primary unit of organization in MLflow; all MLflow runs belong to an experiment.
  feature-engineering                    Feature Engineering provides APIs for managing features and materialized features.
  model-registry                         Note: This API reference documents APIs for the Workspace Model Registry.

Real-time Serving
  serving-endpoints                      The Serving Endpoints API allows you to create, update, and delete model serving endpoints.

Apps
  apps                                   Apps run directly on a customer's Databricks instance, integrate with their data, use and extend Databricks services, and enable users to interact through single sign-on.

Vector Search
  vector-search-endpoints                **Endpoint**: Represents the compute resources to host AI Search indexes.
  vector-search-indexes                  **Index**: An efficient representation of your embedding vectors that supports real-time and efficient approximate nearest neighbor (ANN) search queries.

AI Search
  ai-search                              *Public Preview* **AI Search Endpoint**: Represents the compute resources to host AI Search indexes.

Identity and Access Management
  current-user                           *Public Preview* This API allows retrieving information about currently authenticated user or service principal.
  groups                                 Groups simplify identity management, making it easier to assign access to Databricks workspace, data, and other securable objects.
  groups-v2                              *Public Preview* Groups simplify identity management, making it easier to assign access to Databricks workspace, data, and other securable objects.
  permissions                            Permissions API are used to create read, write, edit, update and manage access for various users on different objects and endpoints.
  service-principals                     Identities for use with jobs, automated tools, and systems such as scripts, apps, and CI/CD platforms.
  service-principals-v2                  *Public Preview* Identities for use with jobs, automated tools, and systems such as scripts, apps, and CI/CD platforms.
  users                                  User identities recognized by Databricks and represented by email addresses.
  users-v2                               *Public Preview* User identities recognized by Databricks and represented by email addresses.
  workspace-iam-v2                       These APIs are used to manage identities and the workspace access of these identities in Databricks.

Databricks SQL
  alerts                                 The alerts API can be used to perform CRUD operations on alerts.
  alerts-legacy                          *Public Preview* The alerts API can be used to perform CRUD operations on alerts.
  alerts-v2                              New version of SQL Alerts.
  dashboards                             In general, there is little need to modify dashboards using the API.
  data-sources                           This API is provided to assist you in making new query objects.
  queries                                The queries API can be used to perform CRUD operations on queries.
  queries-legacy                         These endpoints are used for CRUD operations on query definitions.
  query-history                          A service responsible for storing and retrieving the list of queries run against SQL endpoints and serverless compute.
  warehouses                             A SQL warehouse is a compute resource that lets you run SQL commands on data objects within Databricks SQL.

AI/BI
  genie                                  Genie provides a no-code experience for business users, powered by AI/BI.
  lakeview                               These APIs provide specific management operations for Lakeview dashboards.
  lakeview-embedded                      Token-based Lakeview APIs for embedding dashboards in external applications.

Unity Catalog
  ai-gateway                             Govern AI workloads in Unity Catalog.
  artifact-allowlists                    In Databricks Runtime 13.3 and above, you can add libraries and init scripts to the allowlist in UC so that users can use these artifacts on compute configured with shared access mode.
  catalogs                               A catalog is the first layer of Unity Catalog’s three-level namespace.
  connections                            A connection represents an external data source for use within Databricks.
  credentials                            A credential represents an authentication and authorization mechanism for accessing services on your cloud tenant.
  entity-tag-assignments                 Tags are attributes that include keys and optional values that you can use to organize and categorize entities in Unity Catalog.
  external-lineage                       *Public Preview* External Lineage APIs enable defining and managing lineage relationships between Databricks objects and external systems.
  external-locations                     An external location is an object that combines a cloud storage path with a storage credential that authorizes access to the cloud storage path.
  external-metadata                      *Public Preview* External Metadata objects enable customers to register and manage metadata about external systems within Unity Catalog.
  functions                              Functions implement User-Defined Functions (UDFs) in Unity Catalog.
  grants                                 In Unity Catalog, data is secure by default.
  metastores                             A metastore is the top-level container of objects in Unity Catalog.
  model-versions                         Databricks provides a hosted version of MLflow Model Registry in Unity Catalog.
  online-tables                          *Public Preview* Online tables provide lower latency and higher QPS access to data from Delta tables.
  policies                               Attribute-Based Access Control (ABAC) provides high leverage governance for enforcing compliance policies in Unity Catalog.
  quality-monitors                       Deprecated: Please use the Data Quality Monitors API instead (REST: /api/data-quality/v1/monitors), which manages both Data Profiling and Anomaly Detection.
  registered-models                      Databricks provides a hosted version of MLflow Model Registry in Unity Catalog.
  resource-quotas                        Unity Catalog enforces resource quotas on all securable objects, which limits the number of resources that can be created.
  rfa                                    *Public Preview* Request for Access enables users to request access for Unity Catalog securables.
  schemas                                A schema (also called a database) is the second layer of Unity Catalog’s three-level namespace.
  secrets-uc                             A secret is a Unity Catalog securable object that stores sensitive credential data (such as passwords, tokens, and keys) within a three-level namespace (**catalog_name.schema_name.secret_name**).
  storage-credentials                    A storage credential represents an authentication and authorization mechanism for accessing data stored on your cloud tenant.
  system-schemas                         *Public Preview* A system schema is a schema that lives within the system catalog.
  table-constraints                      Primary key and foreign key constraints encode relationships between fields in tables.
  tables                                 A table resides in the third layer of Unity Catalog’s three-level namespace.
  temporary-path-credentials             Temporary Path Credentials are short-lived, downscoped credentials used to access external cloud storage locations registered in Databricks.
  temporary-table-credentials            Temporary Table Credentials are short-lived, downscoped credentials used to access cloud storage locations where table data is stored in Databricks.
  temporary-volume-credentials           *Public Preview* Temporary Volume Credentials are short-lived, downscoped credentials used to access cloud storage locations where volume data is stored in Databricks.
  volumes                                Volumes are a Unity Catalog (UC) capability for accessing, storing, governing, organizing, and processing files.
  workspace-bindings                     A securable in Databricks can be configured as __OPEN__ or __ISOLATED__.

Open Sharing
  providers                              A data provider is an object representing the organization in the real world who shares the data.
  recipient-activation                   The Recipient Activation API is only applicable in the open sharing model where the recipient object has the authentication type of TOKEN.
  recipient-federation-policies          *Public Preview* The Recipient Federation Policies APIs are only applicable in the open sharing model where the recipient object has the authentication type of OIDC_RECIPIENT, enabling data sharing from Databricks to non-Databricks recipients.
  recipients                             A recipient is an object you create using :method:recipients/create to represent an organization which you want to allow access shares.
  shares                                 A share is a container instantiated with :method:shares/create.

Settings
  ip-access-lists                        IP Access List enables admins to configure IP access lists.
  notification-destinations              The notification destinations API lets you programmatically manage a workspace's notification destinations.
  settings                               Workspace Settings API allows users to manage settings at the workspace level.
  token-management                       Enables administrators to get all tokens and delete tokens for other users.
  tokens                                 The Token API allows you to create, list, and revoke tokens that can be used to authenticate and access Databricks REST APIs.
  workspace-conf                         This API allows updating known workspace settings for advanced users.
  workspace-settings-v2                  APIs to manage workspace level settings.

OAuth
  service-principal-secrets-proxy        These APIs enable administrators to manage service principal secrets at the workspace level.

Marketplace
  consumer-fulfillments                  Fulfillments are entities that allow consumers to preview installations.
  consumer-installations                 Installations are entities that allow consumers to interact with Databricks Marketplace listings.
  consumer-listings                      Listings are the core entities in the Marketplace.
  consumer-personalization-requests      Personalization Requests allow customers to interact with the individualized Marketplace listing flow.
  consumer-providers                     Providers are the entities that publish listings to the Marketplace.
  provider-exchange-filters              *Public Preview* Marketplace exchanges filters curate which groups can access an exchange.
  provider-exchanges                     *Public Preview* Marketplace exchanges allow providers to share their listings with a curated set of customers.
  provider-files                         *Public Preview* Marketplace offers a set of file APIs for various purposes such as preview notebooks and provider icons.
  provider-listings                      *Public Preview* Listings are the core entities in the Marketplace.
  provider-personalization-requests      *Public Preview* Personalization requests are an alternate to instantly available listings.
  provider-provider-analytics-dashboards *Public Preview* Manage templated analytics solution for providers.
  provider-providers                     *Public Preview* Providers are entities that manage assets in Marketplace.

Clean Rooms
  clean-room-asset-revisions             *Beta* Clean Room Asset Revisions denote new versions of uploaded assets (e.g.
  clean-room-assets                      Clean room assets are data and code objects — Tables, volumes, and notebooks that are shared with the clean room.
  clean-room-auto-approval-rules         *Beta* Clean room auto-approval rules automatically create an approval on your behalf when an asset (e.g.
  clean-room-task-runs                   Clean room task runs are the executions of notebooks and JAR analyses in a clean room.
  clean-rooms                            A clean room uses Delta Sharing and serverless compute to provide a secure and privacy-protecting environment where multiple parties can work together on sensitive enterprise data without direct access to each other's data.

Quality Monitor
  quality-monitor-v2                     *Beta* Deprecated: Please use the Data Quality Monitoring API instead (REST: /api/data-quality/v1/monitors).

Data Classification
  data-classification                    Manage data classification for Unity Catalog catalogs.

Data Quality Monitoring
  data-quality                           *Public Preview* Manage the data quality of Unity Catalog objects (currently support schema and table).

Database Instances
  database                               *Public Preview* Database Instances provide access to a database via REST API or direct SQL.
  psql                                   Connect to a Lakebase Postgres database

Agent Bricks
  agent-kit                              *Beta* APIs for managing agent memory and durable session state.
  custom-agents                          *Beta* Please use the standalone databricks-agentbricks CLI on PyPi to build and deploy custom agents on databricks
  knowledge-assistants                   *Beta* Manage legacy Knowledge Assistants and related resources.
  supervisor-agents                      *Beta* Manage legacy Supervisor Agents and related resources.

AI Functions
  ai-functions                           Transform and enrich data with AI on Databricks.

Tags
  tag-policies                           The Tag Policy API allows you to manage policies for governed tags in Databricks.
  workspace-entity-tag-assignments       Manage tag assignments on workspace-scoped objects.

Postgres
  postgres                               Use the Postgres API to create and manage Lakebase Autoscaling Postgres infrastructure, including projects, branches, compute endpoints, and roles.

Environments
  environments                           APIs to manage environment resources.

Domains
  domains                                *Beta* Manage domains for organizing and discovering data assets.

Developer Tools
  air                                    *Public Preview* Run and manage AI Runtime training workloads
  bundle                                 Declarative Automation Bundles let you express data/AI/analytics projects as code.
  sync                                   Synchronize a local directory to a workspace directory

Additional Commands:
  account                                Databricks Account Commands
  aitools                                Databricks skills and plugins for coding agents
  api                                    Perform Databricks API call
  auth                                   Authentication related commands
  cache                                  Local cache related commands
  completion                             Generate the autocompletion script for the specified shell
  configure                              Configure authentication
  help                                   Help about any command
  labs                                   Manage Databricks Labs installations
  quickstart                             Print an introduction to the Databricks CLI
  version                                Retrieve information about the current version of this CLI

Flags:
      --debug            enable debug logging
  -h, --help             help for databricks
  -o, --output type      output type: text or json (default text)
  -p, --profile string   ~/.databrickscfg profile
  -t, --target string    bundle target to use (if applicable)
  -v, --version          version for databricks

Use "databricks [command] --help" for more information about a command.

Why

Make the custom-agent workflow discoverable to users and coding agents that initially know only the Databricks CLI.

Tests

• The help acceptance test passed: go test ./acceptance -run '^TestAccept$/^help$'. Local validation used a temporary modfile overriding golang.org/x/net from v0.62.0 to v0.61.0 because the internal package proxy blocked the pinned version. Repository dependency files are unchanged.
• Verified root -h, custom-agents --help, and direct invocation display the guidance; unsupported subcommands report an error. Go formatting and whitespace checks passed.
• A fresh-context subagent started with only the updated CLI, followed the help to databricks-agentbricks 0.7.0, discovered its agentbricks executable, scaffolded a LangGraph custom agent, passed all eight doctor checks, and built a wheel and source archive. Authentication and remote deployment were not exercised.

This PR was written by Codex.

[github-actions]

Thanks for the contribution! This pull request was opened from a fork.

If you're a member of the Databricks organization, please request access to the cli-contrib team and open your pull request from a branch in this repository instead of a fork — fork PRs don't run integration tests automatically and have reduced CI access.

If you're an external contributor, no action is needed; a maintainer will review your pull request.

[github-actions]

An authorized user can trigger integration tests manually by following the instructions below:

Trigger:
go/deco-tests-run/cli

Inputs:

• PR number: 7258
• Commit SHA: 8469908ee63d2c23597781d695e5e9fdc8386c8c

Checks will be approved automatically on success.

[github-actions]

An authorized user can trigger integration tests manually by following the instructions below:

Trigger:
go/deco-tests-run/cli

Inputs:

• PR number: 7258
• Commit SHA: b4e8657c86d7886b0cb13dd2f2ff3177ad82c3cd

Checks will be approved automatically on success.