import os
from dotenv import load_dotenv
import asyncio
from agents import Agent, Runner, WebSearchTool, ModelSettings, set_default_openai_api
from agents.mcp import MCPServerStdio
from agents.extensions.handoff_prompt import RECOMMENDED_PROMPT_PREFIX
from openai.types.shared import Reasoning
load_dotenv(override=True) # load the API key from the .env file. We set override to True here to ensure the notebook is loading any changes
set_default_openai_api(os.getenv("OPENAI_API_KEY"))
async def main() -> None:
async with MCPServerStdio(
name="Codex CLI",
params={"command": "npx", "args": ["-y", "codex", "mcp"]},
client_session_timeout_seconds=360000,
) as codex_mcp_server:
# Downstream agents are defined first for clarity, then PM references them in handoffs.
designer_agent = Agent(
name="Designer",
instructions=(
f"""{RECOMMENDED_PROMPT_PREFIX}"""
"You are the Designer.\n"
"Your only source of truth is AGENT_TASKS.md and REQUIREMENTS.md from the Project Manager.\n"
"Do not assume anything that is not written there.\n\n"
"You may use the internet for additional guidance or research."
"Deliverables (write to /design):\n"
"- design_spec.md – a single page describing the UI/UX layout, main screens, and key visual notes as requested in AGENT_TASKS.md.\n"
"- wireframe.md – a simple text or ASCII wireframe if specified.\n\n"
"Keep the output short and implementation-friendly.\n"
"When complete, handoff to the Project Manager with transfer_to_project_manager."
"When creating files, call Codex MCP with {\"approval-policy\":\"never\",\"sandbox\":\"workspace-write\"}."
),
model="gpt-5",
tools=[WebSearchTool()],
mcp_servers=[codex_mcp_server],
handoffs=[],
)
frontend_developer_agent = Agent(
name="Frontend Developer",
instructions=(
f"""{RECOMMENDED_PROMPT_PREFIX}"""
"You are the Frontend Developer.\n"
"Read AGENT_TASKS.md and design_spec.md. Implement exactly what is described there.\n\n"
"Deliverables (write to /frontend):\n"
"- index.html – main page structure\n"
"- styles.css or inline styles if specified\n"
"- main.js or game.js if specified\n\n"
"Follow the Designer’s DOM structure and any integration points given by the Project Manager.\n"
"Do not add features or branding beyond the provided documents.\n\n"
"When complete, handoff to the Project Manager with transfer_to_project_manager_agent."
"When creating files, call Codex MCP with {\"approval-policy\":\"never\",\"sandbox\":\"workspace-write\"}."
),
model="gpt-5",
mcp_servers=[codex_mcp_server],
handoffs=[],
)
backend_developer_agent = Agent(
name="Backend Developer",
instructions=(
f"""{RECOMMENDED_PROMPT_PREFIX}"""
"You are the Backend Developer.\n"
"Read AGENT_TASKS.md and REQUIREMENTS.md. Implement the backend endpoints described there.\n\n"
"Deliverables (write to /backend):\n"
"- package.json – include a start script if requested\n"
"- server.js – implement the API endpoints and logic exactly as specified\n\n"
"Keep the code as simple and readable as possible. No external database.\n\n"
"When complete, handoff to the Project Manager with transfer_to_project_manager_agent."
"When creating files, call Codex MCP with {\"approval-policy\":\"never\",\"sandbox\":\"workspace-write\"}."
),
model="gpt-5",
mcp_servers=[codex_mcp_server],
handoffs=[],
)
tester_agent = Agent(
name="Tester",
instructions=(
f"""{RECOMMENDED_PROMPT_PREFIX}"""
"You are the Tester.\n"
"Read AGENT_TASKS.md and TEST.md. Verify that the outputs of the other roles meet the acceptance criteria.\n\n"
"Deliverables (write to /tests):\n"
"- TEST_PLAN.md – bullet list of manual checks or automated steps as requested\n"
"- test.sh or a simple automated script if specified\n\n"
"Keep it minimal and easy to run.\n\n"
"When complete, handoff to the Project Manager with transfer_to_project_manager."
"When creating files, call Codex MCP with {\"approval-policy\":\"never\",\"sandbox\":\"workspace-write\"}."
),
model="gpt-5",
mcp_servers=[codex_mcp_server],
handoffs=[],
)
project_manager_agent = Agent(
name="Project Manager",
instructions=(
f"""{RECOMMENDED_PROMPT_PREFIX}"""
"""
You are the Project Manager.
Objective:
Convert the input task list into three project-root files the team will execute against.
Deliverables (write in project root):
- REQUIREMENTS.md: concise summary of product goals, target users, key features, and constraints.
- TEST.md: tasks with [Owner] tags (Designer, Frontend, Backend, Tester) and clear acceptance criteria.
- AGENT_TASKS.md: one section per role containing:
- Project name
- Required deliverables (exact file names and purpose)
- Key technical notes and constraints
Process:
- Resolve ambiguities with minimal, reasonable assumptions. Be specific so each role can act without guessing.
- Create files using Codex MCP with {"approval-policy":"never","sandbox":"workspace-write"}.
- Do not create folders. Only create REQUIREMENTS.md, TEST.md, AGENT_TASKS.md.
Handoffs (gated by required files):
1) After the three files above are created, hand off to the Designer with transfer_to_designer_agent and include REQUIREMENTS.md, and AGENT_TASKS.md.
2) Wait for the Designer to produce /design/design_spec.md. Verify that file exists before proceeding.
3) When design_spec.md exists, hand off in parallel to both:
- Frontend Developer with transfer_to_frontend_developer_agent (provide design_spec.md, REQUIREMENTS.md, AGENT_TASKS.md).
- Backend Developer with transfer_to_backend_developer_agent (provide REQUIREMENTS.md, AGENT_TASKS.md).
4) Wait for Frontend to produce /frontend/index.html and Backend to produce /backend/server.js. Verify both files exist.
5) When both exist, hand off to the Tester with transfer_to_tester_agent and provide all prior artifacts and outputs.
6) Do not advance to the next handoff until the required files for that step are present. If something is missing, request the owning agent to supply it and re-check.
PM Responsibilities:
- Coordinate all roles, track file completion, and enforce the above gating checks.
- Do NOT respond with status updates. Just handoff to the next agent until the project is complete.
"""
),
model="gpt-5",
model_settings=ModelSettings(
reasoning=Reasoning(effort="medium")
),
handoffs=[designer_agent, frontend_developer_agent, backend_developer_agent, tester_agent],
mcp_servers=[codex_mcp_server],
)
designer_agent.handoffs = [project_manager_agent]
frontend_developer_agent.handoffs = [project_manager_agent]
backend_developer_agent.handoffs = [project_manager_agent]
tester_agent.handoffs = [project_manager_agent]
# Example task list input for the Project Manager
task_list = """
Goal: Build a tiny browser game to showcase a multi-agent workflow.
High-level requirements:
- Single-screen game called "Bug Busters".
- Player clicks a moving bug to earn points.
- Game ends after 20 seconds and shows final score.
- Optional: submit score to a simple backend and display a top-10 leaderboard.
Roles:
- Designer: create a one-page UI/UX spec and basic wireframe.
- Frontend Developer: implement the page and game logic.
- Backend Developer: implement a minimal API (GET /health, GET/POST /scores).
- Tester: write a quick test plan and a simple script to verify core routes.
Constraints:
- No external database—memory storage is fine.
- Keep everything readable for beginners; no frameworks required.
- All outputs should be small files saved in clearly named folders.
"""
# Only the Project Manager receives the task list directly
result = await Runner.run(project_manager_agent, task_list, max_turns=30)
print(result.final_output)
if __name__ == "__main__":
# Jupyter/IPython already runs an event loop, so calling asyncio.run() here
# raises "asyncio.run() cannot be called from a running event loop".
# Workaround: if a loop is running (notebook), use top-level `await`; otherwise use asyncio.run().
try:
asyncio.get_running_loop()
await main()
except RuntimeError:
asyncio.run(main())
