network-ai 3.3.5 → 3.3.6

package/README.md

@@ -4,7 +4,7 @@
 
 [![CI](https://github.com/jovanSAPFIONEER/Network-AI/actions/workflows/ci.yml/badge.svg)](https://github.com/jovanSAPFIONEER/Network-AI/actions/workflows/ci.yml)
 [![CodeQL](https://github.com/jovanSAPFIONEER/Network-AI/actions/workflows/codeql.yml/badge.svg)](https://github.com/jovanSAPFIONEER/Network-AI/actions/workflows/codeql.yml)
-[![Release](https://img.shields.io/badge/release-v3.3.5-blue.svg)](https://github.com/jovanSAPFIONEER/Network-AI/releases)
+[![Release](https://img.shields.io/badge/release-v3.3.6-blue.svg)](https://github.com/jovanSAPFIONEER/Network-AI/releases)
 [![npm](https://img.shields.io/npm/dw/network-ai.svg?label=npm%20downloads)](https://www.npmjs.com/package/network-ai)
 [![ClawHub](https://img.shields.io/badge/ClawHub-network--ai-orange.svg)](https://clawhub.ai/skills/network-ai)
 [![Node.js](https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg)](https://nodejs.org)
@@ -68,7 +68,7 @@ That's it. No config files, no setup wizards. Add more agents, swap frameworks,
 
 > The demo shows a code review swarm, but Network-AI is not a code review tool. The same orchestration pattern works for research pipelines, data processing, content moderation, customer support routing, document analysis, financial workflows — any task where multiple agents need to coordinate without stepping on each other.
 
-> **Live demo source coming soon:** The full source for `04-live-swarm.ts` and `05-code-review-swarm.ts` will be added to the repo with a `.env.example` so you can run them against your own API keys. In the meantime, examples `01`–`03` cover all core framework features — atomic blackboard, FSM governance, parallel dispatch — with no API key or external dependency required.
+> **Run the demo yourself:** `05-code-review-swarm.ts` is in the repo. Copy `.env.example` to `.env`, add your `OPENAI_API_KEY`, then run `npx ts-node examples/05-code-review-swarm.ts`. Supports 4 modes: built-in code review, paste your own code, system design document, or custom role for any content type (proposals, policies, job descriptions, emails). Examples `01`–`03` cover all core framework features with no API key required. `04-live-swarm.ts` (live AI research swarm) is coming soon.
 
 ## Why This Exists -- The Multi-Agent Race Condition Problem
 
@@ -246,6 +246,55 @@ npm run setup -- --list        # List all 12 available adapters
 npm run setup:example          # Generate a starter example.ts
 ```
 
+### Running in PowerShell (Windows)
+
+All commands work in PowerShell. The only difference from bash is how you set environment variables.
+
+**Set your API key for the current session:**
+
+```powershell
+$env:OPENAI_API_KEY = "sk-..."
+```
+
+**Or load it from `.env` automatically** — copy the template first:
+
+```powershell
+Copy-Item .env.example .env   # then open .env and fill in your key
+```
+
+**Run the examples (no API key needed):**
+
+```powershell
+npx ts-node examples/01-hello-swarm.ts
+npx ts-node examples/02-fsm-pipeline.ts
+npx ts-node examples/03-parallel-agents.ts
+```
+
+**Run the interactive launcher** (picks which example to run):
+
+```powershell
+npx ts-node run.ts
+```
+
+**Run the AI code review swarm demo** (requires `OPENAI_API_KEY`):
+
+```powershell
+$env:OPENAI_API_KEY = "sk-..."
+npx ts-node examples/05-code-review-swarm.ts
+```
+
+**Run the tests:**
+
+```powershell
+npm test                      # Core orchestrator (79 tests)
+npm run test:security         # Security module (33 tests)
+npm run test:adapters         # Adapter system (139 tests)
+npm run test:priority         # Priority & preemption (64 tests)
+npm run test:all              # All suites in sequence
+```
+
+> **Tip:** To persist `OPENAI_API_KEY` across sessions, add it to your PowerShell profile or set it as a user environment variable via *System Properties → Environment Variables*.
+
 ### For OpenClaw Users
 
 Copy this skill into your OpenClaw workspace:

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "network-ai",
-  "version": "3.3.5",
+  "version": "3.3.6",
   "description": "AI agent orchestration framework for TypeScript/Node.js - plug-and-play multi-agent coordination with 12 frameworks (LangChain, AutoGen, CrewAI, OpenAI Assistants, LlamaIndex, Semantic Kernel, Haystack, DSPy, Agno, MCP, OpenClaw). Built-in security, swarm intelligence, and agentic workflow patterns.",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",