write-swarm-client

Introduction:

Your task is to create a trainable Agent (or Agent Loop, multi-agent system, etc.) based on the requirements, and provide it to the user for reinforcement learning training. Under the AgentJet reinforcement learning framework, this is very simple.

First, give the agent system a name based on the user's requirements, always place your code at ``tutorial/opencode_build_*, for example opencode_build_math_agent`.

Next, create the directory: tutorial/opencode_build_math_agent

Then, create the Agent source files:

• tutorial/opencode_build_math_agent/agent_roll.py (Use tutorial/example_academic_trans_swarm/trans_roll.py as a template. There aren't many changes — the key is to ask the user for the necessary parameters.)
• tutorial/opencode_build_math_agent/agent_run.py (Create the function or class to run the agent based on the user's requirements. Synchronous or asynchronous are both fine.)
• tutorial/opencode_build_math_agent/readme.md (Agent description, along with training and debugging instructions.)

How to Write the Agent

Write the agent using the OpenAI SDK. It mainly includes the following three functions (along with any necessary sub-functions and sub-modules):