Settings

Every persistent setting, changeable mid-session.

Docs on GitHub

Type /settings to open a dialog with every persistent setting. Changes are written to $ZOT_HOME/config.json and take effect on the next turn — no restart needed. Rows that open a sub-view (like model shortcuts) use esc to go back one level before it closes the dialog.

SettingWhat it controls
render imagesDraw images returned by read inline using the terminal's image protocol (Ghostty, Kitty, iTerm2, WezTerm). Auto-detected from TERM_PROGRAM; the toggle overrides detection. Greyed out and forced off on terminals that speak no image protocol.
auto-swarmLet the main agent spawn background sub-agents in parallel via swarm_spawn.
jail new sessions by defaultStart interactive, print, JSON, RPC, and background-agent runs with tools confined to the working directory. Off by default. Changing it updates the current sandbox immediately; /jail and /unjail only override the current session. Stored as jail_by_default.
tui settingsSub-view for input style, status position, and working spinner position. See TUI settings.
thinking levelReasoning depth: off, minimum, low, medium, high, xhigh, or max. max is a separate opt-in tier above xhigh, sent natively to GPT-5.6 and adaptive-thinking Claude models and clamped on unsupported backends. Also settable per run with --reasoning.
color themeauto/dark/light or any JSON theme from $ZOT_HOME/themes or a loaded extension.
model shortcutsSub-view with nine slots (model 1 ... model 9). Press enter on a slot to open the /model selector and bind a provider/model, backspace to clear it. Then Ctrl+1 ... Ctrl+9 from the editor instantly switch the active model (same cross-provider swap as /model, transcript and cost carried over). No-op while a turn is running.