Task Chains

A task chain is a JSON state machine that defines how the AI agent behaves end-to-end. Chains are composable, inspectable, and backend-agnostic.

Chain structure

{
  "id": "my-chain",
  "description": "What this chain does",
  "tasks": [ /* TaskDefinition[] */ ],
  "token_limit": 8192,
  "debug": false
}

Field	Type	Description
id	string	Unique identifier
description	string	Human-readable description
tasks	TaskDefinition[]	Ordered list of task definitions
token_limit	int	Max token budget for the chat history
debug	bool	Enable verbose task-level logging

Task structure

{
  "id": "step_name",
  "handler": "chat_completion",
  "system_instruction": "...",
  "execute_config": { },
  "transition": { "branches": [ ] },
  "retry_on_failure": 0,
  "timeout": "30s"
}

See Handlers and Transitions for the full field reference.

Sections

• Handlers — all task handler types and their fields
• Transitions & Branching — how the chain decides what to do next
• Annotated Examples — full working chains with commentary