.debug()

.debug()

AgentForceAgent Optional Chainable

Enable debug logging for the agent to output configuration details and runtime information. Currently logs agent name, provider, and model configuration.

Signature

debug(): AgentForceAgent

Returns

Returns the AgentForceAgent instance for method chaining.

Examples:

Basic Usage

Simple Debug

import { AgentForceAgent } from '@agentforce/adk';

const agent = new AgentForceAgent({
  name: "MyAgent"
})
  .useLLM("ollama", "gemma3:4b")
  .systemPrompt("You are a helpful assistant")
  .debug() // Logs: name, provider, model
  .prompt("Hello world");

const response = await agent.output("text");

With Method Chaining

import { AgentForceAgent } from '@agentforce/adk';

const agent = new AgentForceAgent({
  name: "DebugAgent",
  tools: ["fs_read_file"]
})
  .useLLM("google", "gemini-1.5-flash")
  .systemPrompt("You are a code reviewer")
  .task("Read the main.ts file")
  .task("Analyze the code structure")
  .debug() // Enable debug logging
  .prompt("Review this TypeScript code");

await agent.run();

Method Chaining

The debug() method supports fluent chaining and can be placed anywhere in the chain:

const agent = new AgentForceAgent({ name: "ChainedAgent" })
  .debug() // Can be called early
  .useLLM("ollama", "phi4-mini:latest")
  .systemPrompt("You are an assistant")
  .debug() // Or called multiple times
  .prompt("Test prompt");

Note

Note: This method will be extended with additional debugging capabilities in future versions. Currently provides basic configuration logging.

Related Methods

• .useLLM() - Configure LLM provider (logged by debug)
• .systemPrompt() - Set system instructions
• .task() - Add tasks to execution queue
• .run() - Execute agent with debug output