Add Atropos Integration

### **Description**
I wanted to suggest adding support (or at least an example integration) for [Atropos](https://github.com/NousResearch/atropos)

### **Why this matters**
Atropos is becoming a critical component for Reasoning-centric RL (CoT), particularly for:
* **Verifiable Reasoning tasks** (Math, Code, Logic)
* **Deep Reasoning Expansion**
* **Scalable feedback loops** for complex agentic workflows

### **Impact**
While the current ROCK examples are great, having a similar integration for Atropos would:
* **Broaden ROLL's usability**: for the "Reasoning Frontier" in LLM research.
* **Decoupled Scalability**: Leverage Atropos' microservice architecture to keep high-concurrency rollouts independent of the main training loop, ensuring maximum GPU utilization during complex reasoning tasks.

I have already verified this integration locally with a 100-step "Golden Run" (expanding thinking tokens from 218 to 330) and have a PR ready for submission.

Start by reading the current ROCK examples and the Atropos project to understand the proposed integration boundary and microservice workflow. The issue reports a locally verified 100-step Golden Run; done should mean adding support or an example integration that reproduces that run and its reported thinking-token expansion.

Written by the indexing model from the issue text.