Skip to content

Interactive TUI ​

Run rho in a terminal to start an interactive coding session in the current directory.

bash
rho

Rho uses the current directory as its workspace. Tool access follows tools and workspace.

The session runs in the daemon, so a turn keeps going after you quit the TUI. rho --resume picks it up again. --config is refused. Set RHO_HOME to use another config.

Start a session ​

Open a project and run Rho from the repository root:

bash
cd path/to/project
rho

To open the same session with the first prompt already sent:

bash
rho --prompt "summarize this repository"

This is still the interactive TUI. Use rho run when you want one answer and then exit. If you are not signed in yet, the text stays in the composer until you finish login and press enter.

Rho streams the assistant response as it works. Tool use appears inline so you can see commands, file reads, and edits as they happen. For persisted history and resume behavior, see sessions.

If you need auth or a model first, use /login and /model, or follow getting started.

Everyday controls ​

Send a prompt ​

Type a request and press enter to send it. The composer wraps at word boundaries where possible and keeps Unicode grapheme clusters (including emoji sequences and combining marks) together, using their rendered column width. Slash commands, pickers, and the inline shell stay available while MCP servers connect. A model prompt waits until those servers finish connecting or time out; Rho holds the turn and starts it for you once they settle, so you do not press enter twice. Press esc to take a held prompt back into the composer before it starts.

text
summarize this repository
text
add tests for the config parser
text
find where the TUI handles paste events

Use a multiline prompt when you need to paste or write a longer request. Type @ to open a workspace file picker, fuzzy-search paths, then press tab or enter to insert an @path reference. You can also double-click a path to insert it. The picker follows .gitignore, .ignore, and global Git ignore rules while still showing hidden workspace files that are not ignored.

Interrupt, steer, reset, or quit ​

  • Press esc to abort the current response without closing Rho. The provider request and active tool receive the same cancellation signal, partial assistant output remains in the session, and queued prompts are restored to the composer instead of running automatically.
  • Press enter while Rho is working to steer the run. Rho finishes every tool call from the current assistant turn, adds their results to context, then inserts the steering message before the next model request. Once applied, that text appears in the transcript as a user message.
  • Press alt-enter while Rho is working to queue a follow-up that starts after the current turn ends, instead of steering the live run. ctrl-enter does the same thing for terminals that bind alt-enter to fullscreen.
  • Press ctrl-r to reset the conversation history. The next message starts a new session.
  • Press ctrl-c to clear the current input line.
  • Press ctrl-c twice to quit.

Keyboard shortcuts ​

Most editing keys work the way they do in a normal terminal input. Run /help for a searchable overlay of the same shortcuts. Single-line fields in login, configuration, and agent-editing overlays scroll horizontally to keep the insertion point visible, including when you move with Home, End, or the arrow keys. Moving within the visible text keeps the window steady so you can inspect both sides of the insertion point. Secret fields stay masked while scrolling.

KeyAction
escAbort the current response and restore queued work, or hide the command palette when it is open
/ at startOpen the command palette
/helpOpen the keyboard shortcuts overlay
@Open workspace file path autocomplete
$Open skill autocomplete. Sending the prompt loads every mentioned skill first
up / downRe-enter previous prompts from this and earlier sessions, or select a command or file while a picker is open
tabComplete the selected command, skill, or file path, or complete a workspace path in shell mode
ctrl-pCycle to the next pinned model. ctrl-shift-p cycles backward on terminals that report it. Does nothing when no models are pinned
Alt+MCycle permission modes until Rho exits (not saved); during a turn, queue the next mode. Skips Auto without a classifier; configurable as cycle_permission_mode
Alt+UMove the keyboard to the latest surface the ui tool showed: tab and the arrow keys move between its controls, enter or space operates one, and esc returns to the composer
Alt+SCycle output streaming for this TUI, without saving: live → paragraph → off → live. Works during a turn; configurable as cycle_streaming_mode
enterSend a prompt, run a selected slash command, or steer after the current assistant turn while a response is running
alt-enterQueue the composer contents as a follow-up that runs after the current turn ends; while idle, insert a newline. ctrl-enter always works as a fallback for terminals that bind alt-enter to fullscreen (Windows Terminal, Windows Alacritty, WezTerm). Configurable as queue_prompt
alt-upPull the most recent queued prompt back into the composer for editing
ctrl-rSearch previous prompts, newest first. Type to filter, then enter recalls the prompt into the composer; down steps forward and back to your draft. Configurable as search_prompt_history. Start a new session with /new; reset_conversation has no default key
ctrl-fFind text in the transcript. See Find in the transcript. Configurable as search_transcript
pageup / pagedownScroll the transcript viewport
ctrl-gOpen the current composer text in a non-empty $VISUAL, else $EDITOR
ctrl-endJump the transcript viewport back to the bottom
mouse wheelScroll the transcript viewport
left-click and dragSelect transcript text and copy it on release
right-clickPaste clipboard text into the composer
code block COPYCopy the full code block contents
ctrl-cClear input, then quit if pressed again
ctrl-zUndo the last composer edit. Typing undoes a word at a time, and a run of backspace or delete undoes together. Configurable as undo
ctrl-shift-zRedo the last undone edit, on terminals that report it. A new edit clears the redo history. Configurable as redo

See Mouse for clicking pickers, prompts, panels, and the status line.

ctrl-g opens the current composer text in a non-empty $VISUAL, falling back to $EDITOR only when VISUAL is unset or empty, both while idle and while a response is running. Rho temporarily restores the normal terminal before starting the editor and resumes the TUI after the process exits. The editor receives expanded pasted text rather than any collapsed display marker. Rho removes one conventional final line ending from the edited file when it restores the composer. Set VISUAL or EDITOR to an executable path or a platform-native command line with arguments. Rho does not pick a default editor; if neither variable is set or non-empty, it warns with EDITOR is not set.

Vim mode ​

Set /config → Display → Editing mode to vim, or set editing_mode = "vim" in ~/.rho/clients/tui.toml, to edit the main composer with vim-style modes. The menu change applies immediately; a config file edit applies at the next start. The composer rule shows INSERT or NORMAL. Rho starts each draft in insert mode, where keys type as usual. esc switches to normal mode instead of cancelling or aborting; press esc again in normal mode for the usual cancel or abort.

Normal mode supports:

  • Counts before a motion or command, such as 3w or 2dd.
  • Motions: h j k l, w b e and W B E, 0 ^ $, f F t T, gg, and G. A single j or k at the top or bottom row recalls prompt history, like up and down.
  • Operators d, c, and y with a motion, the iw and aw text objects, or doubled for whole lines (dd, cc, yy).
  • x X s S D C Y, r to replace characters, and p P to put the last deleted or yanked text.
  • i a I A o O to return to insert mode.
  • u to undo. Each normal-mode command undoes as one step, including text typed after i, a, o, c, or a similar command, until esc. ctrl-r stays prompt history search; use the redo binding to redo.

enter sends from either mode. Visual mode, . repeat, and named registers are not supported. The side chat prompt, pickers, and other fields keep the default editing keys.

Text streaming ​

Choose how assistant and reasoning text appears under /config → Display → Output streaming. Alt+S cycles it for the running TUI without saving, including during a turn:

  • live, the default, reveals text as it arrives.
  • paragraph reveals text through blank-line boundaries. Whitespace-only blank lines and CRLF line endings count; this does not parse Markdown structure.
  • off holds text until a message boundary, such as reasoning handing off to the answer, a tool handoff, or response completion. It does not wait for the entire agent run.

Switching modes reveals text already received through the normal Markdown renderer, then applies the new mode to subsequent text. Incomplete Markdown stays pending until it can render safely; switching does not end the message or split a code fence. It never hides text already displayed. Model generation, tool execution, tool previews, and cancellation keep running normally; the completed answer is the same. These controls work during a turn without submitting a prompt or restarting the response.

Cancellation and errors reveal held text. A retry discards the failed attempt's pending text.

The config menu and shortcut change the running TUI. Set output_streaming in ~/.rho/clients/tui.toml to choose the startup mode. This does not change provider streaming settings.

Commands ​

Type / at the start of the message box to open the command palette. Keep typing to filter commands, use up and down to select, press tab to complete the selected command, and press enter to run it. With the mouse, click a row to select it, scroll over the palette to move the selection, and double-click a row to complete it like tab. A double click never runs a command. Most built-in slash commands run locally. Commands that start agent work say so below.

Suggestions reflect the current model's capabilities. /fast and its argument suggestions appear only for models that support fast mode, and switching models updates the suggestions immediately. You can still type a hidden command explicitly: unsupported actions explain why they cannot run. /fast off can disable the saved preference even on a model that does not support fast mode.

A single / as the first character opens the command palette. Any later / characters are treated as normal message text and do not reopen the palette.

CommandAction
/add-dir [path]Add a directory to this session's workspace scope. See additional workspace directories. Without a path, lists the added directories. Unavailable during a running turn.
/advisor [on|off|model]Toggle or set advisor mode, which gives the agent an advisor tool backed by a second model. /advisor on without an advisor model opens a picker first; the mode turns on once a model is selected, and esc leaves it off. /advisor model changes the advisor model without changing the mode; esc keeps the current model. Set its reasoning under /config → Agent → Advisor reasoning. The choice saves to configuration through the daemon and applies before the next turn.
/codemode [status|on|only]Set how the always-available codemode tool, which composes other tools (including MCP) in a Starlark script, presents them. on keeps direct tools declared so the model can use either; only hides them by default so work goes through codemode. In either mode, top-level tool_search can explicitly load matches for direct calls on the next model request; script discovery stays read-only. /codemode status (or bare /codemode) shows the mode. Nested calls follow the current /permissions mode exactly like direct calls; there is no separate codemode permission level. The codemode card shows the script with syntax highlighting. When it finishes, the header shows the nested-call count. The choice saves to [codemode] mode and applies to the next model request. See Codemode.
/login [provider]Log in with a provider or an external runtime (Claude Code, Cursor Agent, Antigravity). No args opens a picker; delegated runtimes are marked (delegation only) and nest under a vendor group (Claude Code under Anthropic, Antigravity under Google, Cursor under SpaceXAI). Typing a nested method such as cursor or kimi still finds its group; direct args target a single provider, /login claude-code, /login cursor, or /login antigravity.
/logout [provider]Delete stored provider credentials, or sign out of Claude Code everywhere with /logout claude-code (after confirmation). /logout cursor and /logout antigravity are not available from Rho; run cursor-agent logout, or see Antigravity sign-out. No args opens a picker; direct args target a single provider.
/model [provider/model]Open a picker for models with available auth, or choose a provider/model and save it to configuration. Switching applies at once. If the conversation holds provider-native context the new model cannot use, a notice says what was dropped, and the next send opens a confirm-send modal: send anyway, compact first (compaction summarizes portable context but does not make native blocks sendable), don't send, or send for this session. Send for this session skips the modal for later sends to that model in the same session, and asks again if a native block it did not warn about would be omitted. The picker opens on pinned models when any pin has auth. Press ctrl-o to switch between pinned and all models, and ctrl-p to pin or unpin the highlighted model.
/remember [global] <text>Append one instruction bullet to the project-root AGENTS.md, or ~/.rho/AGENTS.md with global. Applies to the current conversation without starting a model turn; the file is re-read when you start or switch to a different session (/new, /resume of another session, or the next launch). Use a single line; available between turns. See Project and global instructions.
/refresh-modelsRefresh cached model lists for every configured provider and redownload the models.dev catalog.
/fast [on|off]Toggle or set fast mode for models that support it. The choice saves to configuration, appears as (fast) after the model name, and bills at a higher rate. Codex sends a priority service tier. SpaceXAI OAuth grok-4.7 sends grok-4.7-build-fast and stays selected as grok-4.7. Subagents do not inherit it; set fast: true on an agent instead.
/resume [id]Resume a saved session by UUID or prefix. No args opens a picker for other sessions in the current workspace. In the picker, press d or Delete to remove a session after confirmation. If the current model cannot use the session's provider-native context, Rho asks whether to resume with the session model, compact with that model first, or continue on the current model.
/sessionsOpen the session manager for every directory. Sessions group under their directory, current directory first; worktrees of one Git repository share a section, and missing directories collect at the end. Press Enter on a session in the current directory to resume it, or on a directory row to narrow the list to that directory. Sessions from other directories remain available to inspect and delete, but must be resumed by starting Rho in their directory. Press d on a session to delete it, or on a directory row to delete the reviewed saved sessions in that directory, both after confirmation. The current session is never deleted.
/side [prompt]Open a side chat overlay that can see a frozen snapshot of this session (captured when the overlay first opens) and use read-only workspace tools (list_dir, read_file, grep, glob). User and plugin MCP are not attached. It does not write back to the session. Messages use the main transcript renderer, including Markdown in streamed replies and the same user-message styling. Click COPY on a code block to copy its source text. Tool activity shows names, not result cards. Empty /side opens the overlay, or closes it when already open (a running aside keeps going). /side <prompt> opens and sends. Esc cancels a running aside, or closes the overlay when idle. /new and resume discard it.
/btw [prompt]Alias for /side.
/treeNavigate turns and compaction states in the current session. Continuing from an older state creates a branch.
/workflow:<name> [inputs JSON]Start one workspace workflow in the background without opening the list. See Start a workflow by name.
/workflowOpen the workflow list. Start a local workflow or saved plan in the background, watch a run as a dependency graph, or press d to delete a plan/run. Ready runs also offer Retry start to launch the existing run after a startup failure; Watch only inspects it. The run id is appended to chat context and completion is delivered automatically. Reopen /workflow and press Enter on a run to watch; use arrows or hjkl to move between graph nodes.
/rewind [turn]Preview and restore native file-tool changes from a completed turn, then return the conversation to before that turn while preserving the old branch. Enabled by default; opt out with behavior.workspace_rewind = false and restart Rho. It does not reverse shell, Git, process, network, database, or service effects (recorded untracked effects show a limited badge). Conflicting or unsupported paths stay unchanged, and a partial restore leaves conversation state unchanged. Checkpoints from the old experimental version cannot be rewound because they lack pre-turn conversation boundaries. See checkpoint storage and budgets.
/configOpen the settings screen: the session's own options, then the agent's and the TUI's setting categories, changed through the daemon.
/permissions [bypass|auto|allow_edits|plan|supervised]Show or change the permission mode, saving it to configuration. Auto prompts for a classifier model if needed. Available between turns.
/infoOpen a single-pane overlay immediately with the running Rho version, provider, model, reasoning level, permission mode, advisor mode, added workspace directories, and session usage (including session and latest-request cache hit rates, and re-billed cache misses). Claude Code, Cursor Agent, and Antigravity status and session tree facts fill in after the overlay opens. Press c to copy the report, drag to select text, or press Enter or Esc to close. The report does not stay in the transcript.
/contextOpen a single-pane overlay showing what fills the context window, by source: system prompt sections (Rho instructions, each instruction file, the skills listing, any model prompt), tool schemas (built-in, and each MCP server), messages (including any compaction summary), tool results grouped by tool, and request-only host context. The total matches /info and is calibrated to the last provider-reported prompt when available; rows are local estimates (about 4 characters per token) scaled to that total. Press c to copy the report, or Enter or Esc to close. Available between turns.
/changelog [latest]Show release notes for this installed version from the bundled changelog. /changelog latest fetches notes for the newest published release.
/compact [instructions]Immediately summarize older conversation history to reduce future model context. Optional instructions tell the summarizer what must survive, such as the current plan, specific file paths, or an unresolved error (/compact keep the migration plan and the failing test name). This works even when auto-compaction is disabled. Auto-compaction runs the same job before a turn when the context is over the threshold. Both show a compact card; the composer stays usable. Press esc to cancel.
/skillsShow available workspace skills and insert a /skill:<name> command for one. Running the inserted command loads the skill through the skill tool before the model responds. Add text after the command to include extra instructions in the same turn.
/themePreview and apply a color theme. Lists the host terminal theme, built-in light/dark schemes, and custom files from ~/.rho/themes/. Moving the selection previews colors; Enter saves. See Theme.
/hooksReload lifecycle hooks and open a single-pane overlay showing what each one will run: the resolved argv, working directory, timeout, and environment. Also names any project hooks file ignored because the workspace is not trusted. Press Enter or Esc to close.
/agents [create]With no argument, reload agent definitions and browse them grouped by source (yours, workflow, shared, built in, internal). Each agent shows a fact sheet (runtime rho, claude-cli, cursor, or antigravity; model policy; reasoning; tools; source file) and a short prompt excerpt. Enter edits agents under ~/.rho/agents or the project, configures the model of a reserved internal agent, and opens the full prompt read-only for everything else. Press Delete on one of your agents to delete its definition file after confirmation. /agents create [request] starts the guided agent creator when the active agent has skill, questionnaire, read_file, write, and rho. The creator writes the file with write, then checks it with rho action agents.
/create-agent [request]Alias for /agents create.
/initSurvey the repository and create or update its root AGENTS.md with project-specific instructions. Preserves existing instructions with targeted edits. Start or switch sessions (/new, /resume) afterward to reload them. Requires skill, write, and file-edit tools; unavailable in Plan mode or during a model turn. See Project and global instructions.
/attachOpen a picker of subagents from this directory and watch one in place. See Activity rail.
/diffOpen a popup listing changed files under Staged, Unstaged, and Untracked, with the selected file's patch beside them. ↑↓ or Tab/Shift+Tab move between files, → scrolls the patch, and typing filters by path. Patches load per file on selection, and nothing is added to the transcript. A clean worktree opens the popup with a worktree clean notice.
/doctorOpen a single-pane diagnostics dashboard. Rows are grouped into Authentication, Providers, Runtimes, Workspace, Extensions, and Daemon, each with a status marker (✓ ok, · info, ! warning, ✗ failure) and a hint under any issue. The overlay opens immediately with the instant checks; provider endpoints, the Claude Code binary and login, cursor-agent, agy, rtk, and the daemon are probed in the background and fill in as they answer, so it works during a model turn. Authentication lists only signed-in auth modes plus the active one, which warns when its key is missing; unused providers without credentials are omitted. Cursor Agent and Antigravity rows stay informational when the runtime is missing or signed out; the Antigravity row (agy) runs agy --version and agy models and warns when agy is older than 1.5.0. No secrets are displayed. Press Esc or Enter to close. The same checks run headlessly with rho doctor [--json]; see automation CLI.
/jobsList every job the daemon runs, grouped by project, with its status, title, model, run time, and cost. Subagents and workflow runs show under the session that started them. Keys: ↑/↓ select, Tab jumps to the next job that needs input, y, a, or d allow once, allow for the session, or deny a waiting permission prompt, m sends a message, c twice cancels the turn, n starts a session, / filters, and Enter attaches. Press Tab while starting a session to give it its own worktree. Attaching to a session of another project moves the TUI to that session's directory. Answer plan approvals and questions after you attach.
/mcpList configured MCP servers for this session, including in-flight connects. Connecting servers are not treated as failures. /doctor includes the same MCP health row. See Model Context Protocol.
/limitsOpen a single-pane overlay with the usage windows reported by connected providers. Codex OAuth, Kimi Code OAuth, SpaceXAI OAuth, and OpenCode Go are supported when logged in; absent windows are omitted. The overlay opens immediately with cached or last-observed values, then fills in live windows as each provider responds. When Claude Code is signed in, Rho drives the Claude Code TUI /usage panel (claude-agent-acp --cli) over a PTY (token stays in Claude) and shows those windows live. Last-observed windows remain as fallback if the probe fails. Press esc or enter to close.
/usageAlias for /limits.
/todoOpen the latest task checklist without a model request, including while the agent is working. The overlay updates live, highlights the in-progress item, and opens with it in view. Use ↑↓, PgUp/PgDn, Home/End, or the mouse to scroll; Enter/Esc closes without moving the conversation. The checklist survives compaction and resume; /new clears it.
/spendOpen a single-pane overlay that summarizes every model request in the usage ledger on this machine: the equivalent API cost, a spend chart, and cost and token tables for models, providers, and purpose. Tab/Shift+Tab (or ←/→) switch between Today, 7 days, 30 days, and All time. It opens on Today, which charts spend per hour. Spend is split into actual (the cost the provider reported) and computed (tokens priced at today's cached models.dev rates when the provider reported none), so subscription usage shows its API equivalent rather than your bill. Models merge across routing prefixes (x-ai/grok-4.6 and grok-4.6 are one row). Prices come from the same models.dev lookup as the statusline (including a custom host's catalog_mode); a route with no price of its own borrows the same model's price from another provider. Each table shows its top five rows and folds the rest into one N more row. Built-in Ollama models show as local, rows with no price show —, and the summary counts unpriced requests. Reopening shows the last result at once while a fresh read runs. Press c to copy the visible range, or Enter or Esc to close. The ledger is opened read-only.
/export [path]Export the current session transcript. Formats: HTML (default), Markdown (.md), JSON (.json). Omit the path to write a timestamped file under ~/.rho/exports/ (or $RHO_HOME/exports/). A directory argument receives that default file name. The path extension selects the format. Existing files are not overwritten; choose a new path. HTML exports render assistant Markdown math (inline $...$ or \(...\), display $$...$$ or \[...\]) with KaTeX. Live TUI math uses a narrower TXM path; see Math rendering.
/copyOpen an output tree for the current conversation, preview an assistant message, and press Enter to copy it. Works while a response is running and with --no-save. Esc closes without copying.
/newStart a new session and re-read global and project AGENTS.md instructions from disk. Switching to another session with /resume or tree selection also reloads instructions; model switches and same-session tree navigation keep the cache. Clears the transcript, composer, and attachments. The next message creates a new session folder. Unavailable while a model turn is running.
/clearAlias for /new.
/title <name>Rename the current session. Replaces any auto-generated title.
/helpShow keyboard shortcuts and composer controls in a searchable overlay.
/exitQuit the TUI.

Custom prompt templates loaded from prompt files or [prompt_templates] also appear in the command palette. Completing one inserts its prompt into the composer so you can add or edit text before sending. A template with argument placeholders lists them in its usage hint and completes to its command instead, so you can type the arguments first. Submitting a template during a running turn queues its expanded text as steering, just like a regular prompt.

Pickers ​

Some commands replace the message box with a picker. Use up and down to select, type to filter by case-insensitive regex, press tab to autocomplete the filter from the highlighted item, press enter to confirm, and press esc to cancel. In conversation and internal-agent model pickers, press ctrl-p to pin or unpin the highlighted model; pinned models are saved in config and shown first in both picker types. Press ctrl-o to switch the list between all authenticated models and pinned models only. /config starts with a short category browser. Its search matches the settings listed inside each category. Press enter to open a category or a setting and esc to return; enter on an on/off setting toggles it in place. Changes save at once and return to the same category so you can keep adjusting its settings.

Short confirmations and some credential prompts use an inline list instead of a filterable picker. The arrow marks the focused option, with its label in bold and its shortcut beside it. Explanations wrap beneath each label, and the list scrolls to keep the focused option visible in short terminals. Use Up/Down or Left/Right to move, Enter or Space to choose, or press an option's shortcut to choose it immediately. Unavailable options are dimmed and skipped. Esc cancels or returns to the parent picker.

/limits uses the same overlay chrome as those pickers, but as a single scrolling pane of usage bars rather than a two-column list. It is not a picker: up and down scroll, and enter or esc close it.

/side (and /btw) uses that same overlay chrome with its own transcript and prompt. Enter sends to the aside. Esc closes the overlay without cancelling its reply, so you can keep using the main chat while the aside runs in the background. Use /side or /btw again to return to its transcript and any unsent draft. The aside's prompt edits like the main composer: Shift+Enter (or the newline binding) adds lines, word and arrow keys move the caret, Up and Down recall the aside's own earlier prompts, large pastes collapse into a marker, the external editor binding opens the draft, and clicking or dragging places the caret and selects text. The prompt stays pinned below the aside's transcript while the transcript scrolls. Ctrl+C clears the aside's prompt first; with an empty prompt, it cancels only the running aside and does nothing when the aside is idle. Up and Down scroll the aside's transcript when the prompt is empty and there is no earlier prompt to recall.

Login and models ​

/login, /logout, and /model behavior, including Claude Code and Cursor handoff, is on Authentication and models. Logging in does not normally switch the active model. If Rho started without usable auth, a successful login selects that provider's default model.

Press ctrl-p on a highlighted picker row to pin or unpin that model. Pins are stored in model.favorite_models and appear first, in pin order, in conversation and internal-agent pickers. From the composer, ctrl-p cycles that list forward, and ctrl-shift-p cycles backward on terminals that report it. Both are configurable as cycle_pinned_model and cycle_pinned_model_back under [keybindings] in ~/.rho/tui.toml. The picker's pin toggle follows cycle_pinned_model. Its all/pinned toggle follows toggle_tool_output.

The picker opens on the pinned list when any pin has auth. ctrl-o switches between pinned and all authenticated models. That view lasts for the session. Unpinning the last visible pin while the pinned list is open returns the picker to all models. Direct /model provider/model and /model @alias still resolve against the full catalog.

Cycling pins maps an unsupported reasoning level to a supported one. An ordinary /model or picker switch still rejects an incompatible explicit level. A cycle requested during a provider turn applies when the queued switch lands.

/model stays available during a run. The current run keeps its model through the remaining steps and tool calls. Rho applies the queued change after the agent loop ends, before the next queued message. Selecting another model before then replaces the pending choice. If the finished conversation holds provider-native context the new model cannot use, the switch lands with an omission notice and each queued message is confirmed before it is sent.

Compaction does not make provider-native blocks sendable, and it does not prove a provider cache is warm. If handoff compaction fails or produces no reduction, Rho keeps the source model active.

Internal agent overrides: Internal agent models.

Mouse ​

Everything clickable reacts when you hover over it. In pickers, prompts, and palettes, a single click selects or focuses and a double click does what enter would. Buttons such as copy targets, status line fields, and an attachment's ✕ act on a single click.

  • Pickers: click a row to select it and double-click to choose it. The wheel scrolls the list.
  • Questionnaires, approvals, and confirmation prompts: click a choice to focus it and double-click to confirm it. Clicks are ignored until the prompt has been drawn, so a stray click cannot move an approval off Deny before you see it.
  • /, $, and @ palettes: click a row to select it, and scroll over the palette to move the selection. Double-click completes the row like tab; it never runs a command.
  • Panels and side chat (/limits, /doctor, /hooks, /info, /spend, /side, and similar): drag across text to copy it, drag the scrollbar to scroll, and click a copy target to copy it.
  • Status line: click the model, provider, or reasoning to open /model; context, cost, or rate to open /info; permission mode to open its picker; and a sign-in warning to open /login.
  • Attachments: click the ✕ after a queued attachment's label to remove it. Clicking the preview or label does nothing, and a double click removes only one attachment.

Status line ​

Approval prompts are documented with permission modes. plan, auto, and supervised appear dim. bypass appears in warning style.

When the workspace is a Git repository with a GitHub remote and gh is on PATH, the status line shows the current branch's pull request number next to the path. Ready-to-merge PRs are green. Merge conflicts, failing checks, or requested changes are red.

While advisor mode is on, the top composer divider names the reviewing model, for example advisor: anthropic/claude-fable-5. It reads advisor: no model when the mode is on but no model is set. Nothing reviews the session in that state. Advice arrives as an advisor tool card.

Removed commands ​

Rho 3 removed /goal and /computer. For /goal, state the outcome you want in your prompt. Upgrading to Rho 3 lists everything else that changed.

Questionnaires ​

A form with several questions shows one question at a time. Up and Down move among that question's choices. Tab moves to the next question, and Shift+Tab moves to the previous question. Enter confirms the current question and moves forward, or submits on the last question. Esc cancels the form. The footer under the choices lists the keys that apply.

You can also use the mouse. Click a question's tab to show it, and click a choice to select it; on a multi-select question, each click toggles the choice. Double-clicking a single-select choice confirms it like Enter.

Confirmation prompts, such as deleting a session, work the same way: click an option to focus it, and double-click it to confirm.

Questionnaire fallbacks ​

A questionnaire normally blocks until you submit or cancel it. You can opt in to timed fallback answers through /config → Agent → Questionnaire timeout. Enter positive seconds or clear the field for Disabled. The setting is off by default and is captured when each form opens.

The model must supply a separate on_timeout plan; a preselected default is not enough. Timed forms show the remaining seconds, fallback answers, and the reason for proceeding. Any keyboard, paste, or mouse interaction pauses the countdown permanently for that form. Nothing automatically submits while you edit. Mouse movement counts as interaction, even without a click. Explicit submit still returns your answers with source: "user". Expiry returns the proposed fallback with source: "timeout_fallback" and a transcript notice, not a user message. Neither fallback answers nor silence grant authorization. Fallbacks are for safe, reversible decisions, never permissions, purchases, destructive actions, or other authorization.

Timeouts are serviced by the UI event loop, with input taking priority. Heavy event traffic can delay a fallback; it never makes it run early.

Activity rail ​

Live turns, background agents, and process jobs hang off a spinner at the bottom of the transcript. Click a row to attach or peek. Details: Activity rail.

Attachments ​

Paste images with ctrl+v when a host clipboard helper is available, or drop a filesystem path. Rho accepts PNG, JPEG, GIF, and WebP images and extracts text from common document types into a bounded attachment.

Details: Attachments.

Transcript display ​

The TUI owns the transcript viewport (use its scroll controls, not terminal scrollback). Headings, copy actions, jump-to-bottom, and stale-stream handling are documented separately.