Assistance is optional and provider-dependent
AI can help explain terminal output or prepare an action, while supported voice workflows can turn speech into input or use a configured speech service. These tools depend on the provider, device permissions and capabilities enabled in your release.
A local history suggestion is different from a model request. Do not assume that an encrypted terminal connection also makes a prompt private from the AI provider receiving it.
Configure an AI connection
- Open Settings → AI and review the available connection modes.
- Select the intended provider, endpoint and model where those controls are offered.
- For My API key, enter the key in API key for this session.
- Check the provider's data handling and costs before submitting sensitive material.
- Test with non-sensitive input and review the result before using it on a real server.
The session API key stays in memory and must be entered again after reload; it is not included in workspace exports or sync. Browser access can require the provider's browser-origin support or an approved HTTPS Gateway. Do not work around a failed browser request by sending the key to an unknown proxy.
Installed coding-agent support
Installed host coding agent is a separate inference source. The current selector offers supported Claude Code and Gemini CLI inference; Codex and OpenCode are marked inference unavailable. The current Gemini inference path requires Gemini CLI 0.21.3 on the connected host. Installing either unavailable command-line tool does not enable its inference integration. You can still use an installed tool through an ordinary authorized terminal; that is a different workflow.
Review context and voice permissions
Depending on the selected feature, prompts, selected terminal context or speech may be processed by the configured service. Review that service before sharing passwords, private output or recordings. A terminal screenshot or pasted image can reveal more than the question you intended to ask.
Grant microphone access only for a voice workflow you intend to use. Check the selected speech provider rather than assuming audio stays on the device. Stop the active voice operation when finished; revoke operating-system or browser permission when it is no longer needed.
A suggestion is not a safety guarantee
Inspect generated commands, paths and destinations before execution. Models can misunderstand an environment or produce incorrect actions. For automated file and command access, read agents and tasks and connected assistants, where explicit permissions matter beyond ordinary text suggestions.