Skip to main content

​
Logging

RadarOS includes a built-in Logger with colored terminal output and structured agent run formatting. Control verbosity via logLevel in AgentConfig.

​
Logger Class

The Logger is used internally by agents. You can also instantiate it directly: 
import { Logger } from "@radaros/core";

const logger = new Logger({
  level: "info",
  color: true,
  prefix: "myapp",
});

logger.info("Agent started");
logger.debug("Tool call", { toolName: "getWeather", args: { city: "Tokyo" } });

​
LogLevel

LevelOrderUse Case
debug0Tool call details, arguments, results
info1Agent start/end, token usage, duration
warn2Warnings
error3Errors
silent4No logging (default for agents)

​
Setting logLevel in AgentConfig

Control agent logging with the logLevel property: 
const agent = new Agent({
  name: "ToolBot",
  model: openai("gpt-4o"),
  tools: [weatherTool],
  logLevel: "debug",  // "debug" | "info" | "warn" | "error" | "silent"
});
  • "debug" — Logs tool calls, arguments, and results (verbose).
  • "info" — Logs agent start, output, token usage, and duration.
  • "silent" — No logs (default).

​
What Gets Logged

When a run begins: agent name and input preview.
At debug level: tool name and arguments.
At debug level: tool name and result preview (truncated).
At info level: prompt tokens, completion tokens, total tokens.
At info level: wall-clock duration (ms or seconds).
When a run completes: output preview and summary.

​
LoggerConfig

PropertyTypeDefaultDescription
levelLogLevel"info"Minimum level to log.
colorbooleanprocess.stdout.isTTY !== falseEnable colored output. Auto-disabled when not a TTY.
prefixstring"radaros"Prefix shown in log lines. Agents use their name as prefix.

​
Colored Terminal Output

The logger uses ANSI escape codes for colored output:
  • Cyan — Agent name, box borders
  • Magenta — Tool names
  • Green — Token counts, success indicators
  • Yellow — Duration, string values
  • Gray — Timestamps, metadata
  • Red — Errors
Box-drawing characters (┌, │, └, ─) create a structured layout for agent runs.

​
Example Output

With logLevel: "info": 
┌─ Agent: ToolBot ───────────────────────────────────────────────────────
│ Input:   What's the weather in Tokyo? Also, what's 42 * 17?
│
│ Output:  Tokyo is 22°C and sunny. 42 * 17 = 714.
│
│ Tokens: ↑ 245  ↓ 38  Σ 283
│ Duration: 1.2s
└────────────────────────────────────────────────────────────────────────
With logLevel: "debug", additional lines appear for each tool call: 
│ ⚡ getWeather
│   { "city": "Tokyo" }
│ ✓ getWeather →
│   Tokyo: 22°C, sunny
│
│ ⚡ calculator
│   { "expression": "42 * 17" }
│ ✓ calculator →
│   714

​
Example: Enabling Logging

const agent = new Agent({
  name: "assistant",
  model: openai("gpt-4o"),
  logLevel: "info",
});