Web-on-the-Fly/AGENTS.md

Web On The Fly

Flask app that streams AI-generated fake websites via SSE.

This is a Podman project. Use podman instead of docker for all container commands.

Commands

• uv run app.py — start dev server on port 5000
• uv run pyright app.py — typecheck (strict mode in pyproject.toml)
• uv run ruff check app.py — lint
• uv run ruff check app.py --fix — auto-fix lint issues

Run lint/typecheck after any code changes.

Architecture

• Single file: app.py
• / → returns a loading page with spinner + live character counter
• /stream → SSE endpoint; streams LLM output base64-encoded per chunk
• Client JS buffers chunks in-memory (not localStorage), then replaces the document on [DONE]

Env vars (loaded from .env via python-dotenv)

• OPENAI_API_KEY — required
• OPENAI_API_URL — OpenAI-compatible endpoint (default: aipi.reeseapps.com)
• MODEL — model name (default: turbo)

Key details

• LLM is called with stream=True; chunks are base64-encoded to avoid SSE protocol breaks
• HTTP timeout is 300s (long generations)
• Themes defined in THEMES list: tuples of (site_type, description) (fake_store, fake_wiki, fake_social, etc.)
• pyright is configured in strict mode; use # noqa: BLE001 for intentional broad exception catches