coding-agentslisted

# Coding Agents Use a real interactive Terminal Session for the coding agent's entire lifecycle. The external agent, the vBot agent, and the user share the same live terminal. Terminal Sessions survive individual Runs, so an external agent may keep working after the Run that started it ends. ## Non-negotiable rules 1. Use `terminal` and launch the CLI's normal interactive command. Do not convert the task into a one-shot or machine-output invocation. 2. Keep the exact `terminal_id` returned by `start`. Use that same live Terminal Session for questions, approvals, follow-up instructions, and later work instead of starting another process. 3. Treat quiet output as an activity boundary, never as proof of completion. Use `wait`, then inspect `status` and the rendered screen. 4. Do not disable approvals, permission checks, or sandboxes merely to avoid interaction. Answer safe, unambiguous prompts through the TUI; ask the user when the choice carries meaningful authority, risk, cost, or product intent. 5. The user may take control of the same terminal in the WebUI. Before sending sensitive input such as an approval or menu selection, reread `status` and use `expected_screen_revision` so stale input is rejected. 6. Never put credentials or secrets in task text. If login or trust setup appears, leave the Terminal Session available for the user and explain what needs attention. ## Start or reuse First call `list`. Reuse the intended live Terminal Session when one already exists. I