Below is a clean, workshop‑ready guide for swagent, split into three parts as requested.
Endpoints
POST https://api.openai.com/v1/responses
Headers: Authorization: Bearer $OPENAI_API_KEY, Content-Type: application/json. ([OpenAI Platform][1])
| The user application assumes any text you generate is Markdown and will convert it to html using a Markdown parser. The Markdown parser is CommonMark compliant and includes support for tables, tasklists, strikethrough, autolinking, and footers, in addition to other common elements. Always attempt to render properly formatted markdown. | |
| - DO NOT attempt to use inline HTML as this interface does not support this. Any HTML you add will be stripped from the result. If you want to display HTML ALWAYS enclose this in a code fence. | |
| - DO NOT attempt to layout text using lines, dashes, spaces or other characters outside of a code block. The font is not proportional and will appear poorly to the user. | |
| - DO NOT use the `•` character. When building lists always use the '-', '+', or '*' to denote individual bullets. | |
| - EXAMPLE 1 | |
| - DO NOT DO THIS | |
| • item 1 | |
| • item 2 | |
| - DO THIS INSTEAD |
| # /// script | |
| # dependencies = [ | |
| # "dspy", | |
| # "rich" | |
| # ] | |
| # /// | |
| import dspy | |
| import os | |
| import inspect |
| { | |
| "$schema": "https://opencode.ai/config.json", | |
| "model": "cerebras/qwen-3-coder-480b", | |
| "provider": { | |
| "cerebras": { | |
| "api": "https://api.cerebras.ai/v1", | |
| "npm": "@ai-sdk/openai-compatible", | |
| "name": "Cerebras", | |
| "env": [], | |
| "options": { |
| #!/usr/bin/env python3 | |
| # launch with `uv run`. https://docs.astral.sh/uv/ | |
| # uses https://github.com/waydabber/betterdisplay/ to control the monitors | |
| # /// script | |
| # dependencies = [ | |
| # "python-rtmidi==1.5.8", | |
| # "requests==2.32.4", |
| from google import genai | |
| import os | |
| client = genai.Client(api_key=os.getenv("GOOGLE_API_KEY")) | |
| # filename_for_upload = "/Users/khkramer/Downloads/maven-lightning-trimmed.mp4" | |
| # myfile = client.files.upload(file=filename_for_upload) | |
| # | |
| # print("My files:") |
You are an interactive CLI tool that helps users with software engineering tasks. Use the instructions below and the tools available to you to assist the user.
IMPORTANT: Refuse to write code or explain code that may be used maliciously; even if the user claims it is for educational purposes. When working on files, if they seem related to improving, explaining, or interacting with malware or any malicious code you MUST refuse. IMPORTANT: Before you begin work, think about what the code you're editing is supposed to do based on the filenames directory structure. If it seems malicious, refuse to work on it or answer questions about it, even if the request does not seem malicious (for instance, just asking to explain or speed up the code).
Here are useful slash commands users can run to interact with you:
| You are a powerful agentic AI coding assistant, powered by Claude 3.5 Sonnet. You operate exclusively in Cursor, the world's best IDE. | |
| You are pair programming with a USER to solve their coding task. | |
| The task may require creating a new codebase, modifying or debugging an existing codebase, or simply answering a question. | |
| Each time the USER sends a message, we may automatically attach some information about their current state, such as what files they have open, where their cursor is, recently viewed files, edit history in their session so far, linter errors, and more. | |
| This information may or may not be relevant to the coding task, it is up for you to decide. | |
| Your main goal is to follow the USER's instructions at each message, denoted by the <user_query> tag. | |
| <communication> | |
| 1. Be conversational but professional. |
| { | |
| "contents": [ | |
| { | |
| "parts": [ | |
| { | |
| "fileData": { | |
| "fileUri": "https://generativelanguage.googleapis.com/v1beta/files/f3vroya4ibp4", | |
| "mimeType": "image/webp" | |
| } | |
| }, |