Dagu

Appearance

AI agent Settings ​

The AI agent Settings page in the Web UI (/agent-settings) configures the built-in steward itself.

This is broader than workflow action: agent.run or workflow action: chat.completion configuration.

It controls:

  • The Web UI assistant
  • The model registry used by the built-in steward
  • Tool permissions and bash command policy from /agent-tools
  • Model-native web search and provider-backed web tools from /agent-tools
  • The default profile/personality
  • Prerequisites for Workflow Operator on Slack, Telegram, Discord, and LINE

If you are looking for workflow YAML configuration, see Agent Step and Chat & LLM.

Start Here ​

The settings surface is split into smaller pages:

  • Models & Providers for enabling AI agent, adding models, choosing a default model, and understanding model fields
  • OpenAI Subscription for connecting a ChatGPT subscription and using the openai-codex provider
  • OpenCode for Kimi, DeepSeek, GLM, Qwen, and other models via an OpenCode subscription
  • Tool Permissions & Bash Policy for deciding which tools AI agent may use and how bash commands are filtered
  • Web Search for selecting model-native search, Tavily, or Firecrawl
  • Personality for selecting a default profile

What This Page Does Not Replace ​

  • It does not replace workflow action: agent.run settings in DAG YAML
  • It does not replace workflow action: chat.completion settings in DAG YAML
  • It does not configure chat-bot platform tokens for Slack, Telegram, Discord, or LINE

Those are separate features with their own documentation.

  1. Enable AI agent
  2. Add at least one model
  3. Set the default model
  4. Review tool permissions and bash command policy
  5. Optionally select a default profile
  6. Optionally enable web search
  7. Only then configure Workflow Operator (Chat Bot)

Relationship to Workflow Features ​

Workflow action: agent.run ​

The settings page does not replace the agent workflow step. The agent step is a separate DAG feature for running a multi-turn tool-calling loop inside a workflow. See Agent Step.

Workflow action: chat.completion ​

The settings page also does not replace the chat workflow step. action: chat.completion is a workflow feature for direct LLM calls in DAGs. See Chat & LLM.

Workflow Operator (Chat Bot) ​

Workflow Operator depends on the built-in steward being configured first. Slack, Telegram, Discord, and LINE conversations are routed into steward sessions, so AI agent must already have a working model and policy configuration.

See:

See Also ​

Released under the MIT License.

Copyright © 2024 Dagu Contributors