Skip to content
For Self-Managed AI Platform users running v11.1, see the on-premise platform documentation
エージェント型AI > Agent Assist > Environment and commands reference

Environment and commands reference

This page provides a quick reference for environment variables, how the assist LLM is chosen, important files and directories, the list models prompt command, and slash commands.

環境変数

The variables that can be set in the environment or in .env.

特徴量 必須 説明 Default / notes
DATAROBOT_API_TOKEN Yes (unless provided by DR CLI configuration) LLM Gateway（デフォルトプロバイダー）用DataRobot APIキー。 —
DATAROBOT_ENDPOINT いいえ DataRobot API endpoint. https://app.datarobot.com/api/v2
AGENT_ASSIST_LLM_BASE_URL いいえ Base URL for the OpenAI-compatible LLM used by Agent Assist. For more information, see Change the Agent Assist LLM. Derived from DATAROBOT_ENDPOINT (for example, …/genai/llmgw)
AGENT_ASSIST_LLM_MODEL_NAME いいえ Model name for the base LLM used by Agent Assist. For more information, see Change the Agent Assist LLM. anthropic/claude-sonnet-4-5-20250929
AGENT_ASSIST_LLM_API_KEY いいえ API key for the LLM provider. Falls back to DATAROBOT_API_TOKEN
LOGFIRE_TOKEN いいえ Logfire token for tracing. —
DATAROBOT_CLI_CONFIG いいえ Override path to DR CLI configuration file. Default: ~/.config/datarobot/drconfig.yaml
AGENT_ASSIST_CONFIG いいえ Override path to Agent Assist configuration file. Default: ~/.config/datarobot/agent_assist_config.yaml

Files and directories

The paths and files used or created by DataRobot Agent Assist. All paths are relative to the current working directory when you start dr assist.

空のディレクトリでdr assistを実行する

dr assistは、専用の空のディレクトリからのみ実行します。 コードやその他のファイルが含まれるディレクトリでこのコマンドを実行するのは安全ではありません。 エージェントアシストのコーディングワークフローを使用すると、アシスタントはDataRobot Agent Application Templateのクローンを現在のディレクトリに作成します。 この操作によって既存のファイルが上書きされたり競合が発生したりする可能性があり、既存のプロジェクトが損なわれ、アシスタントの出力精度が低下する恐れがあります。 dr assistを実行する前に、専用のディレクトリがない場合は、ディレクトリを作成してそこでターミナルを開きます（たとえば、mkdir my-agent && cd my-agentを実行してから、dr assistを実行します）。

パス 説明
agent_spec.md 現在の作業ディレクトリ内のエージェント仕様ファイル（YAMLコンテンツ）。設計中にアシスタントによって作成されます。 See Agent specification reference for field definitions and examples.
.env Optional environment file in the current directory; same variable names as above.
.datarobot/cli/versions.yaml Used by dependency check; defines minimum tool versions.
~/.config/datarobot/drconfig.yaml DR CLI configuration (token, endpoint). This path can be overridden with DATAROBOT_CLI_CONFIG.
~/.config/datarobot/agent_assist_config.yaml Agent Assist configuration (optional LLM base URL, model name, API key). This path can be overridden with AGENT_ASSIST_CONFIG.
~/.config/datarobot/agent_assist/settings.yaml Global DataRobot CLI / Agent Assist preferences (for example language). Does not set the assist LLM model; use AGENT_ASSIST_LLM_MODEL_NAME in the environment or .env. For more information, see Change the Agent Assist LLM.
config.yaml Optional repository-level configuration; can set repository (url, branch, target_dir, tag) for the template clone.

list models command

At the $ prompt, type list models (two words, no leading slash) to print the Available LLM Gateway Models list from your DataRobot LLM gateway. Agent Assist shows a table with a row index, Model Name (for example azure/gpt-5-1-2025-11-13 or bedrock/anthropic.claude-sonnet-4-5-20250929-v1:0), Provider (such as Anthropic, Azure OpenAI, Amazon Bedrock, Google Vertex AI, or Together AI), and a short Description. After the table, the output includes how many models are listed, a reminder of which model the session is configured to use, and a prompt to either change the model or continue the conversation.

The exact models and providers depend on your organization’s gateway configuration and entitlements. Which model the session uses is determined as described in Choose and change the LLM model.

Apart from list models and the slash commands below, use natural language at the $ prompt for design, coding, and deployment tasks.

Slash commands

Built-in session commands that start with / at the $ prompt. Typing / alone lists these commands and suggests /help for details.

Command エイリアス 説明
/reset /new Clear session state and start fresh (removes agent_spec.md and template directory, clears conversation).
/help /? List commands or show help for a command: /help [command].
/quit /exit Exit the session (with confirmation).

Change the Agent Assist LLM

At runtime, Agent Assist uses the model identified by AGENT_ASSIST_LLM_MODEL_NAME. The base LLM for Agent Assist is configurable, using any value the DataRobot LLM gateway exposes, in the same form as in the list models catalog (for example azure/gpt-5-1-2025-11-13 or anthropic/claude-sonnet-4-5-20250929).

For this setting, when more than one value is configured, the resolution priority is:

  1. Environment variable set in the shell or profile (for example export AGENT_ASSIST_LLM_MODEL_NAME=<gateway-model-id> before dr assist).
  2. .env file in the current working directory—the directory from which you run dr assist. Agent Assist loads .env from that directory.
  3. Built-in default when the variable is unset: anthropic/claude-sonnet-4-5-20250929.

If you are not using the default DataRobot LLM gateway routing, point Agent Assist at an OpenAI-compatible API by setting AGENT_ASSIST_LLM_BASE_URL, AGENT_ASSIST_LLM_MODEL_NAME, and usually AGENT_ASSIST_LLM_API_KEY (see the environment variables table). Adjust these in the environment or in .env as above.

Agent Assist model considerations

Consider the following when choosing and changing the LLM model:

  • ~/.config/datarobot/agent_assist/settings.yaml is for global CLI preferences such as language. It does not configure AGENT_ASSIST_LLM_MODEL_NAME or replace the environment (.env) default behavior for the assist LLM.
  • There is no in-session command (such as /model) to switch the LLM. After you change AGENT_ASSIST_LLM_MODEL_NAME (or related variables), exit and start a new dr assist run to reload the settings.

Broader precedence for credentials, endpoint, and optional YAML (including agent_assist_config.yaml when used) is summarized under Set configuration variables on the installation page.