TESTING

A testing guide for NeuroLink’s Multi-Agent Networks feature, where several AI agents work together on a task. It explains how to prepare the project and run the continuous test suite.

In plain words
What is it for?
Use it when setting up the test environment, installing dependencies, building the project, configuring an AI provider, and running or reviewing integration tests.
Why use it?
It gives developers a repeatable way to check that agents, routing, messages, and provider connections work together. It also covers tests that use real AI services and require API keys.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/juspay/neurolink/testing
Clone the repo
git clone --depth 1 https://github.com/juspay/neurolink
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,562 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.01562
Opus 5 $0.00000 $0.00781
Sonnet 5 $0.00000 $0.00312
Haiku 4.5 $0.00000 $0.00156

Measured yesterday against content hash 31d70255409b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

TESTING scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

docs/agents/TESTING.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Multi-Agent Networks Testing Guide

Overview

This document provides comprehensive guidance for testing the Multi-Agent Networks feature in NeuroLink.

Prerequisites

Environment Setup

  1. Node.js: Ensure Node.js 18+ is installed
  2. pnpm: Install pnpm package manager
  3. Dependencies: Install project dependencies
# Install dependencies
pnpm install

# Build the project
pnpm run build

Required Environment Variables

For integration tests with real providers, set the following:

# Provider API Keys (at least one required for integration tests)
export OPENAI_API_KEY="your-openai-key"
export ANTHROPIC_API_KEY="your-anthropic-key"
export GOOGLE_AI_STUDIO_API_KEY="your-google-ai-key"

# Test configuration
export TEST_PROVIDER="vertex"  # or openai, anthropic, etc.
export TEST_MODEL="gemini-2.0-flash"  # optional model override
export VERBOSE="true"  # enable debug logging

Test Structure

The agent feature uses a single continuous test suite rather than individual vitest unit test files.

Continuous Test Suite

Located at test/continuous-test-suite-agents.ts:

  • Self-contained TypeScript script run directly with tsx
  • Covers all components: Agent, AgentNetwork, MessageBus, topologies
  • Uses fixture files from test/fixtures/agents/
  • Reports pass/fail per test case with timing

Test Fixtures

Located in test/fixtures/agents/:

test/fixtures/agents/
├── agent-definitions.json   # Agent configurations
├── network-topologies.json  # Network topology configs
├── routing-rules.json       # Routing decision test cases
└── messages.json            # MessageBus test payloads

Running Tests

Run the Agent Test Suite

# Run the continuous integration test suite
pnpm exec tsx test/continuous-test-suite-agents.ts

# With verbose output
VERBOSE=true pnpm exec tsx test/continuous-test-suite-agents.ts

# With a specific provider
TEST_PROVIDER=openai pnpm exec tsx test/continuous-test-suite-agents.ts

Read the full file on GitHub · 272 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 272 lines · 0 tokens per session scan A 31d70255409b

Subscribe to this mod's changes

TESTING is an agent published in the GitHub repository juspay/neurolink (128 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,562 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.