@revenium/google-core

Core utilities and shared functionality for Revenium Google middleware packages.

Overview

This package provides the foundational components used by @revenium/google-genai and @revenium/google-vertex middleware packages. It is designed as an internal dependency and is not intended for direct use in applications.

What's Included

• Logger - Configurable logging system for middleware operations
• Metering - Core metering and tracking functionality
• Revenium Client - HTTP client for Revenium API communication
• Types - Shared TypeScript interfaces and types
• Utilities - Common helper functions and tools

Installation

This package is automatically installed as a dependency when you install @revenium/google-genai or @revenium/google-vertex:

npm install @revenium/google-genai
# or
npm install @revenium/google-vertex

You typically do not need to install this package directly.

Usage

This package is consumed internally by the middleware packages. If you're building applications, you should use @revenium/google-genai or @revenium/google-vertex instead.

For middleware package developers:

import { Logger, Metering, ReveniumClient } from "@revenium/google-core";

Tool Metering

Track execution of custom tools and external API calls with automatic timing, error handling, and metadata collection.

Quick Example

import { meterTool, setToolContext } from "@revenium/google-core";

// Set context once (propagates to all tool calls)
setToolContext({
  agent: "my-agent",
  traceId: "session-123"
});

// Wrap tool execution
const result = await meterTool("weather-api", async () => {
  return await fetch("https://api.example.com/weather");
}, {
  operation: "get_forecast",
  outputFields: ["temperature", "humidity"]
});
// Automatically extracts temperature & humidity from result

Functions

meterTool(toolId, fn, metadata?)

• Wraps a function with automatic metering
• Captures duration, success/failure, and errors
• Returns function result unchanged

reportToolCall(toolId, report)

• Manually report a tool call that was already executed
• Useful when wrapping isn't possible

Context Management

• setToolContext(ctx) - Set context for all subsequent tool calls
• getToolContext() - Get current context
• clearToolContext() - Clear context
• runWithToolContext(ctx, fn) - Run function with scoped context

Metadata Options

| Field | Description | |-------|-------------| | operation | Tool operation name (e.g., "search", "scrape") | | outputFields | Array of field names to auto-extract from result | | usageMetadata | Custom metrics (e.g., tokens, results count) | | agent, traceId, etc. | Context fields (inherited from setToolContext) |

Configuration

The core package respects the following environment variables:

• REVENIUM_METERING_API_KEY - API key for Revenium service
• REVENIUM_METERING_BASE_URL - Base URL for Revenium API (default: https://api.revenium.ai)
• REVENIUM_LOG_LEVEL - Logging level (DEBUG, INFO, WARN, ERROR)

Package Information

• Version: 0.1.1
• License: MIT
• Repository: revenium-middleware-google-node

Related Packages

• @revenium/google-genai - Google AI middleware
• @revenium/google-vertex - Vertex AI middleware

Documentation

For complete documentation, see:

• Main Repository README
• @revenium/google-genai Documentation
• @revenium/google-vertex Documentation

Support

For issues, feature requests, or contributions:

• GitHub Issues
• Documentation
• Email: [email protected]

Contributing

See CONTRIBUTING.md

Security

See SECURITY.md