Output Gate

The Output Gate is ToolMesh’s content control layer. JavaScript policies run before (pre) and after (post) every tool execution, enabling input validation, output filtering, and PII redaction.

How It Works

Gate policies are JavaScript files in the policies/ directory. They are executed by goja, a Go-native JavaScript engine.

Pre-Gate (Input Validation)

Runs before the tool executes. Can reject the call or modify parameters.

policies/block-dangerous-params.js

function evaluate(context) {
  if (context.params.force_delete === true) {
    return { allow: false, reason: "force_delete is blocked by policy" };
  }
  return { allow: true };
}

Post-Gate (Output Filtering)

Runs after the tool executes. Can redact sensitive data from the response.

policies/redact-pii.js

function evaluate(context) {
  let output = JSON.stringify(context.result);
  // Redact email addresses
  output = output.replace(/[\w.-]+@[\w.-]+\.\w+/g, "[REDACTED]");
  return { allow: true, result: JSON.parse(output) };
}

CallerClass-Based Filtering

The gate receives the CallerClass, enabling tiered content filtering:

CallerClass	Filtering
trusted	Credentials only
standard	High-risk PII + credentials
untrusted	All PII patterns

Configuration

GATE_EVALUATORS=goja           # Enable goja evaluator (default)

Place policy files in the policies/ directory. ToolMesh loads them at startup.

Enterprise: Compliance-LLM

The enterprise extension adds an LLM-based gate evaluator that classifies content against compliance rules. This enables policies like “block responses containing financial advice” without writing regex patterns.