Implement Sandbox Settings Feature & non AI agent secret management

User requests a Sandbox setting feature to control command execution and resource access within AgentsRoom. Key requested permissions include allowing or denying commands, path locations (inside or outside projects), and filename patterns via prefix or regex. Additionally, the user suggests a UI to manage these permissions easily. A special feature requested is custom slash commands to combine bash or file scripts for shorthand commands, reducing AI token usage. The user also proposes secret management in dev mode to securely inject secrets at runtime (e.g., into .env files) without AI agents accessing or reading them. The team should design and implement a comprehensive Sandbox permission system with UI controls, support for custom slash commands, and secure secret injection mechanisms.

This gathers what several people told us separately. Their original messages stay private: only this rewording is public, and nobody sees who wrote what.

Discussion1

• The team6 days ago

  Thanks for taking the time to send this. We're cleaning up older requests, and this one isn't on our roadmap for now, so we're closing it. If it still matters to you, please submit a new request describing how you'd use it today: fresh requests with current use cases are the ones we look at first.

You will be told by email and in the app on every reply. Every message carries a link to stop them.