Conversation View
- Desktop, mobile and web
- All plans
What it does
Every agent pane has two faces: the raw terminal of the CLI, and the Conversation view, a chat-style rendering of the same session read from the transcript the CLI writes on disk. You switch between the two at any time; the CLI keeps running underneath whichever one is on screen.
The thread reads like a conversation, not a log. Since 2026-11-04 it follows the look of a messaging app: your messages sit in a bubble filled with the accent colour on the right (or a quiet neutral colour with Settings > Appearance > Your messages > Neutral) (when you answer a question, that question is quoted above your bubble), the agent's answers sit in a neutral grey bubble on the left with no name or face (the pane header already names the agent), and under each answer a Done line with the time carries the copy and listen buttons. A burst of tool calls is one folded line centered between the messages (3 steps · Read · Bash, tap or click to unfold). A question the agent asks shows as a white card inside its bubble headed YOUR TURN. The thread uses the full width of the pane, like the terminal it replaces, and markdown is rendered (Mermaid diagrams included). Answers a full-screen CLI repainted over stay readable in full. This layout (bubbles, signed answers, folded tool calls) shipped in 1.178.0. Since the same version a question the agent asks with options (Claude Code's question tool) also appears in the thread as a card you can answer by clicking.
While the agent writes, its answer appears in the thread as fast as in the terminal (since 2026-10-12, Claude Code, Codex and Antigravity CLI): the CLI only saves a block of text to its transcript once the block is finished, so the view reads the answer the terminal is drawing and shows it as plain text, then swaps it for the saved, formatted version as soon as the CLI writes it.
The view is also the way to work in a right-to-left language: Arabic or Hebrew text cannot be laid out on a terminal grid, so for those interface languages the pane opens on the conversation by default.
Video (1 min 12): Conversation view, shown in the real app. A Claude Code agent fixes a bug in a long terminal, one click on Conversation turns the session into a chat, Show tool calls brings the calls back, a follow-up is answered in the thread, and Terminal brings the raw terminal back.
Where to find it
- Floating buttons at the top right of the agent pane, last one under scroll and fullscreen: the Conversation button (a message icon, in the accent colour), which becomes Terminal (a terminal icon) while the conversation is up. It moved there from the pane header on 2026-11-05, stays available in fullscreen, and no mode or Interface elements setting can hide it.
- Conversation toolbar, in the agent pane header while the conversation is up (since 2026-11-05; when the header lacks room they fold behind a … button, and in fullscreen or the full remote workspace they keep their own row above the thread): Summary, the tool-call filter (an icon button labelled Show tool calls / Hide tool calls), Session trace, Copy the conversation, Refresh.
- Line N messages between agents in the thread, with one button per sender; toolbar button Show messages between agents / Fold messages between agents (only when the thread has some).
- Eye button (Hide tool calls…) that appears when you hover the header of a tool-call group in the thread: hides tool calls for good, at the scope you pick.
- Settings > Terminal > Conversation view: Auto, Always or Never. The same choice exists per project under Project settings > Terminals.
- Settings > Terminal > Tool calls in the conversation view: Shown or Hidden. The same field exists under Project settings > Terminals and in Edit agent, with a third option Inherit (the hint Currently: Shown / Currently: Hidden tells what the wider scope gives).
- Agent running on another of your computers (Remote Fleet, since 2026-10-20): the same floating Conversation / Terminal button at the top right of its pane, also in the full remote workspace. The thread, the live answer and the cards are read on the other computer and the cards are answered there. See Remote Fleet.
- Phone: in the agent console, the last floating button at the top right (under fullscreen, filled in the accent colour, as on the desktop) is Show the conversation / Show the terminal, and the conversation screen has Back to the terminal. While the conversation is up, the dock also carries the tool-call filter (Hide tool calls / Show tool calls), and each tool-call group has the eye button (Hide tool calls…), always visible since a finger cannot hover.
How to use it
- Open an agent and click the floating Conversation button at the top right of the pane. The pane switches to the transcript, scrolled to the latest turn. Every message you send from the composer jumps the thread back to the bottom, even if you had scrolled up to read older turns.
- Read the thread. Tool calls between two answers are grouped under a header such as 3 tool calls, open by default: click the header to fold the group (folded, it lists the tool names), click one tool line to see it in full (Show in full / Back to one line). Since 2026-10-14 tool calls are hidden by default: the toolbar filter (Show tool calls) brings them back for this pane only and until it is closed, Settings > Terminal changes it for good; Copy the conversation copies the whole thread; Refresh re-reads the file. To hide tool calls permanently, hover a group header and click the eye button (Hide tool calls…). The dialog Hide tool calls? asks where the choice lands: Only for <agent name> (saved agents only), For every agent of this project or Everywhere; click Hide. The dialog reminds you where to show them again: the toolbar of the view, Settings > Terminal, the project settings or the agent's settings.
- Hover a message for its actions: Copy, and on an agent answer Listen (read aloud), Fork from here and Reply. Reply quotes that answer at the top of the composer (a long answer is quoted by its last lines, where the questions usually are); type your answer under it and send: the agent receives the quote with your reply, so a short "yes" or "1" is never ambiguous. On the phone the same Reply icon sits under each agent answer while the agent's console is open. Select any text and the same selection bar as in the terminal appears: Summarize, Explain, Copy, Send to an agent, Quote in composer, Send to backlog, plus the pane actions.
- Answer a question card. When the agent stops to ask something with options, the card shows The agent is waiting for your answer, the numbered options with their description and, for a single-choice question, Other: write your own answer. One question with one choice is sent as soon as you click an option; several questions, a multiple choice or a typed answer end with Submit answers. The card then shows Sending your answer to the agent… and folds to Answered with your choice once the CLI has recorded it. A question closed in the terminal without an answer reads Question dismissed without an answer.
- Click the floating Terminal button (or press Esc while the thread has the focus) to go back. From the keyboard, Cmd+Shift+T (macOS) / Ctrl+Shift+T (Windows, Linux) switches the focused agent between its terminal and its conversation, both ways (since 2026-11-13); the button's tooltip shows the current shortcut. It acts on the agent whose terminal, message box or conversation has the focus (with the focus elsewhere, the agent open in the current project), never types anything into the terminal or the message box, and keeps what you typed and where you scrolled in each view. Back on the terminal, the keyboard goes straight to the CLI, so you can use its own autocomplete and slash menu, then press the same keys to return. Esc typed in the composer goes to the agent and interrupts its turn, as in the CLI: the pane stays on the conversation (since 2026-11-13). Your last explicit choice is remembered per agent for the rest of the app session.
- When the CLI needs you in its own interface (a permission prompt, a
/modelpicker, a plan dialog, a full-screen screen), the pane hands itself back to the terminal so you cannot miss it, then returns to the conversation once the CLI is done. A question card is the exception: the pane keeps the conversation, since you can answer from there.
Messages between agents. When several agents work together, a mail from a colleague and what the agent does with it (reading its inbox, replying) fold into one line such as 3 messages between agents, followed by the name of each sender. Your own messages, the agent's questions and its longer answers never fold, and the last thing it said about an exchange stays visible. Click the line to open the whole exchange, or a name to open that agent's messages only. Hook output folds the same way when tool calls are shown. The Show messages between agents button in the toolbar opens everything for this pane until it is closed; Settings > Terminal changes it for good.
While the agent works, the Working line (or "<agent name> : working") floats above the composer whatever your scroll position. Very long sessions show Showing the last N messages.; the full history stays on disk.
When an agent compacts its session (its context was full), the conversation does not show the summary as a giant answer any more: a short centred line Session compacted sits where it happened, folded. Click it to read the summary, click again to fold it. When the CLI saved no readable summary, the unfolded line says "No readable summary was saved for this compaction." The line stays visible even with tool calls hidden, is never read aloud, and changes nothing in the agent's own context: it only tells you why the agent no longer remembers the earlier detail.
Settings
preAcceptFolderTrust(global, synced with your account; Settings > AI providers > Claude tab, under the permission mode: Trust the folders I launch agents in):true(default) = before an agent starts on your default Claude account, AgentsRoom answers Claude Code's "Accessing workspace / Yes, I trust this folder" for the folder you launch it in, so the agent does not stop on that question. Applies in Autonomous and Manual mode. Project files such as hooks and MCP servers then load without this warning.false= Claude asks in the terminal. The home folder always asks, whatever the setting: Claude keeps no answer there. Accounts you added and the folders AgentsRoom created itself stay trusted either way. Not for an SSH launch. Applies to the next launch, desktop and phone alike.conversationViewDefault(global, Settings > Terminal > Conversation view): which face a pane opens on.auto(default) opens the conversation for a right-to-left interface language and, since 2026-10-01, in the Simple interface mode (even for a brand-new agent); otherwise the terminal.onalways, including the first launch of a new agent (since 2026-11-07): the pane opens on the empty thread while the CLI starts, and a prompt only the CLI can show, such as a login, still borrows the pane.offnever. The walkthrough also offers Terminal or Conversation; left untouched it staysauto. Since 2026-10-08, changing the resolved preference also updates open panes unless you explicitly chose their view; a changed preference waits for the session id if necessary. A session id arriving on its own never switches a first-launch terminal: withauto, a new agent stays on the terminal until you switch.conversationViewDefault(project override, Project settings > Terminals): the same three values for one project; Follow the global setting again removes the override.conversationToolCalls(global, Settings > Terminal > Tool calls in the conversation view):hide(default since 2026-10-14, the prose only) orshow(each burst of calls as a foldable group). A project (project settings) and a saved agent (Edit agent) can each override it; the narrowest scope wins: agent, then project, then global.conversationToolCalls(project override, Project settings > Terminals): the same two values for one project; Inherit removes the override.conversationToolCalls(agent override, Edit agent): the same two values for one agent; Inherit falls back to the project, then the global value. The eye button in the thread writes the same setting at the scope you pick.- The phone follows
conversationToolCallstoo (since 2026-10-13): the desktop resolves it (agent, then project, then global) and sends it with the thread, and the phone's eye button writes it on the desktop at the scope you pick. The global value is the one of the computer the phone is connected to. conversationToggleShortcut(global, synced with your account; Settings > Keyboard shortcuts > Switch Terminal / Conversation): the chord that switches the focused agent between its terminal and its conversation. Empty (default) =Mod+Shift+T(Cmd+Shift+T on macOS, Ctrl+Shift+T on Windows and Linux). Click the button and press the new keys; the chord must hold Cmd, Ctrl or Alt (or be a function key) and cannot be one another AgentsRoom shortcut already uses. The reset button (or Backspace while recording) goes back to the default. Plain Ctrl+T still reaches the CLI. Works in detached project windows too.conversationAgentTraffic(global, Settings > Terminal > Messages between agents in the conversation view):fold(default since 2026-11-04, mail between agents, inbox reads, replies and hook output in one line) orshow(every message in the thread). Global only, follows your account, and the phone honours it.conversationKeepScrollOnSend(global, Settings > Terminal > Keep my place when I send): off by default, sending a message from the conversation view jumps to the latest reply. On, the view stays where you are reading and only follows new output when you were already at the bottom. The phone's conversation view already behaves like this. Has no effect on the terminal view.
Agent tools (MCP)
settings_get/settings_set: read or writeconversationToolCallsat theglobal,projectoragentscope.agents_save: acceptsconversationToolCalls(show/hide, an empty string removes the agent's override).
The view itself is a reading surface; agents keep working in their own CLI.
Providers
The view exists only for CLIs whose transcript AgentsRoom can read back: Claude Code, Codex, Grok Build, Mistral Vibe (since 2026-09-15), oh-my-pi (since 2026-09-25) and Antigravity CLI (since 2026-09-30). On any other provider the pane stays on the terminal, and the history panel lists only the messages you sent (This agent's CLI does not expose a transcript yet: only the messages you sent are listed.). Reasoning blocks are shown when the CLI saved them, and marked Reasoning not saved by the CLI otherwise.
The clickable question card is Claude Code only: it renders Claude Code's question tool (AskUserQuestion), the one CLI that records a question with options in its transcript. Codex records no such question, and the other CLIs record no question card either.
Permission prompts (since 2026-10-01): when Claude Code asks "Do you want to proceed?" or Codex asks "Would you like to run the following command?" / "Would you like to make the following edits?", the pane no longer drops back to the terminal. A card floats above the composer with the question, Allow, Deny and More choices in the terminal (for the CLI's other rows, such as "Yes, and don't ask again"). Allow types the CLI's own "allow once" key (1 for Claude Code, y for Codex), Deny types Esc, only after checking the prompt is still on screen. Antigravity's approvals and every other CLI prompt (model picker, plan, trust folder) still borrow the pane and give it back once answered. The answer travels through the CLI's own dialog: AgentsRoom replays the keystrokes a human would type, so the CLI sees a normal answer.
Mistral Vibe is a special case: its interface always runs full screen and has no plain-scrollback mode, so a long turn looks frozen in the terminal until the final repaint. The conversation view reads the session log Vibe writes in its own home folder, appended after every model turn, which makes it the live progress feed of a Vibe agent. Vibe does not announce its session id while it runs, so AgentsRoom attributes the newest session started in the agent's working directory after the console opened; the view stays empty until Vibe has saved its first turn.
oh-my-pi: AgentsRoom picks the session file of an oh-my-pi agent itself when it starts it, so the view knows where the conversation is from the first second, with nothing to guess even with several oh-my-pi agents in the same folder. oh-my-pi prints inline (no full-screen mode), so the terminal stays the default and the conversation view is a switch. When you rewind a session inside oh-my-pi (/tree, /branch), only the branch you are on is shown.
Antigravity CLI (agy, the Gemini models): the view reads the transcript agy writes for every conversation in its own folder (~/.gemini/antigravity-cli/brain/). agy saves the model's reasoning in clear, so the reasoning of each answer is shown. The view fills once agy has saved the first turn (within about fifteen seconds): AgentsRoom recognises the conversation the agent's own process holds open (macOS, Linux), or on Windows the one its launch message started. A conversation started by typing /clear inside agy is followed on macOS and Linux; on Windows the view keeps the previous one until the agent is restarted. An Antigravity agent started on a remote SSH host has no view.
Remote SSH (since 2026-10-28): a Claude Code or oh-my-pi agent of a project that runs on a remote SSH host writes its transcript on the host, and the view reads it there. The first opening downloads the conversation once (compressed), then only what the agent added since, checked every few seconds while the view is open. Needs a connection AgentsRoom can reach without a prompt (SSH key or agent, or a terminal of that host already open; on Windows a password-only connection cannot be read in the background). When the host cannot be reached, the view shows only the messages you sent, and the Terminal view still has everything. Codex, Antigravity, Pi and the other CLIs started on a host have no view yet: AgentsRoom does not know which conversation they write there.
Mobile
Present. The phone's agent console opens on the terminal stream and the floating Show the conversation button at the top right switches to the same transcript, read by the desktop and sent encrypted; the choice is remembered per agent while the app is open, like on the desktop. The thread looks the same: accent bubble on the right for you (neutral when the desktop's Your messages setting says so) (with the quoted question when you answer one), grey bubble without a name for the agent, a Done line under each answer, tool calls folded in one centered N steps line (tap to unfold, tap a line to see it in full), the same YOUR TURN question card with the same words. Answering from the phone goes through the desktop, which types the answer into the CLI exactly as a click on the desktop card would; the card is clickable only while the agent's console is open on the desktop, otherwise it reads Answer this question in the terminal.
The answer being written also reaches the phone (since 2026-10-12, Claude Code, Codex, Antigravity CLI), read by the desktop from the agent's open pane and refreshed every few seconds. Phone-only differences: the Copy answer button in the Done line under every agent answer is always shown instead of appearing on hover (it copies the whole answer, ready to paste in another app), there is no selection bar and no read-aloud (a passage is copied through the native text selection; on iPhone a long press on a paragraph copies that whole paragraph, and a long press on your own bubble copies your whole message), web addresses written in clear in an answer are links that open in the phone's browser (since 2026-10-09, as on the desktop), and no floating "working" line since the phone's conversation is read-only and sending stays in the terminal screen. The "tool calls" setting is ported since 2026-10-13: the phone hides the tool groups (and the harness and reasoning lines) whenever the desktop's resolved setting says Hidden, the dock carries the same filter as the desktop toolbar (Hide tool calls / Show tool calls, until you leave the conversation), and the eye button opens the same Hide tool calls? sheet, saved on the desktop through the same path as its own dialog. With a desktop older than this, the phone shows the tool calls and offers the filter but not the eye button. Grok, Mistral Vibe, oh-my-pi and Antigravity answers are readable there since their transcript readers exist. When a CLI runs full screen, the console shows This agent runs full screen, which is hard to show here. with an Optimize for mobile button that relaunches the same session in the CLI's plain-scrollback mode; that button exists for Grok only, because Mistral Vibe has no such mode.
Limits
- The live answer (text appearing while the agent writes) covers Claude Code, Codex and Antigravity CLI. On Grok Build, Mistral Vibe and oh-my-pi the answer appears once the CLI has saved it. The live text is plain (no bold, no headings) until the saved version replaces it, and it needs the agent's pane to be open in AgentsRoom on the desktop. After a tool call, Claude Code receives the first part of the answer (about 2,000 characters) in one block and prints it at once in the terminal too: the view types that block out over about a second instead of showing it in one go, so its last words can appear up to a second or two after the terminal.
- No transcript, no answers: on providers other than Claude Code, Codex, Grok Build, Mistral Vibe, oh-my-pi and Antigravity CLI the pane opens on the terminal, and the view, opened by hand, lists only the messages you sent. Question cards: Claude Code only.
- The question card drives Claude Code's own dialog with keystrokes, checked against Claude Code 2.1.274 and 2.1.276. If the CLI changes that dialog again, the card still shows the question but says The answer did not reach the agent. Answer it in the terminal.; the terminal is always there as the fallback. A multiple-choice question offers no Other free-text row.
- Mistral Vibe: no session resume, so the attributed session id lives only as long as the console is open; a second live Vibe agent in the same project folder is not attributed, to avoid mixing two conversations.
- The remembered per-agent choice lives in memory only; restarting the app returns to the configured default.
- The view reads the CLI's own file, so an answer the CLI did not persist (some reasoning, some full-screen dialogs) cannot appear.
Common questions
- Sending a message jumps the conversation to the end and I lose my reading place. Can it stay where I am? Yes: turn on Settings > Terminal > Keep my place when I send. The conversation view then stays where you are reading after each send, and still follows the new output when you are already at the bottom. By default the view jumps to the latest reply so you see your message leave and the answer arrive.
- Is there a keyboard shortcut to switch between the terminal and the conversation? Yes: Cmd+Shift+T on macOS, Ctrl+Shift+T on Windows and Linux, on the agent that has the focus, both ways. What you typed and your scroll position are kept in each view. Change it under Settings > Keyboard shortcuts > Switch Terminal / Conversation. Not on the phone, which has no physical keyboard.
- How do I answer one specific question of a long thread? Click Reply under the agent answer that asked it (desktop: hover the answer; phone: the icon under it). The answer is quoted at the top of the composer and goes with your message. To quote only a passage, select it and choose Quote in composer in the selection bar.
- Why does Claude no longer ask me to trust the folder? Can I get that question back? Launching an agent in a folder from AgentsRoom counts as your decision, so since 2026-11-07 AgentsRoom answers that question for you on your default Claude account. Hooks and MCP servers of that project then load without the warning, so only launch agents in folders you trust. To get the question back, turn off Settings > AI providers > Claude > Trust the folders I launch agents in. In your home folder Claude always asks.
- My coordinator's conversation is full of mail between agents and I lose its questions. Since 2026-11-04 that traffic folds into one line (N messages between agents) and the agent's questions stay in the thread. Click the line to read the exchange, or a sender's name to read only that agent's messages. To see everything all the time, choose Shown under Settings > Terminal > Messages between agents in the conversation view.
- Can a message meant for me end up folded? Your messages, question cards and long answers never fold, and the last thing the agent said about an exchange stays visible. A short acknowledgement followed by another exchange does fold: it is one click away in the line.
- My agent runs on a remote SSH host and the conversation shows only my messages. Its transcript lives on the host. Since 2026-10-28 the view reads it there for Claude Code and oh-my-pi agents; update AgentsRoom, and check that the host can be reached without typing a password (SSH key, or a terminal of that host open). Other CLIs on a host still show only your messages: use the Terminal view.
- Where did the tool calls go? Can I see them for one project only? Since 2026-10-14 they are hidden by default, and existing installs were switched to hidden once at the update (a project or agent setting you had chosen is kept). Click Show tool calls in the view's toolbar for this pane, or pick Shown in Settings > Terminal > Tool calls in the conversation view (everywhere), in the project settings (one project) or in Edit agent (one agent). The narrowest scope wins.
- How do I answer a question from the Conversation view? Click an option on the card. A single-choice question goes out on the click; otherwise pick your answers (or type one under Other: write your own answer) and click Submit answers. The card turns to Answered once the CLI records it. Works with Claude Code; on the phone the console must be open on the desktop.
- I ticked several options and clicked Submit answers, but the terminal dialog stayed open with the boxes ticked. Fixed on 2026-09-18. Claude Code 2.1.276 changed its multiple-choice dialog: Enter on a row now ticks or unticks it, and only the button under the last row validates. The card now moves to that button before confirming, on the desktop and from the phone. If it happens again, answer in the terminal; the card says so when its answer did not go through.
- Where do I see the detail of a tool call? In the N tool calls block under the answer: each line is cut to one line, click it (Show in full) to read it whole, click again (Back to one line) to fold it. The toolbar filter hides every tool call at once when you only want the prose.
- How do I stop seeing tool calls for good? Hover a N tool calls header, click the eye button (Hide tool calls…) and pick Only for <agent name>, For every agent of this project or Everywhere. Or set Tool calls in the conversation view to Hidden in Settings > Terminal, Project settings > Terminals or Edit agent. The toolbar's Hide tool calls button only lasts while the pane is open.
- I hid the tool calls and want them back. Click Show tool calls in the toolbar for this pane, or set the field back to Shown (or Inherit) in the settings screen where you hid them. Changing the setting anywhere also clears the toolbar's temporary choice.
- Can I read only the agent's answers on my phone? Yes, since 2026-10-13. The phone follows Tool calls in the conversation view set on the desktop (globally, per project or per agent). In the conversation, the dock's filter button (Hide tool calls / Show tool calls) switches them until you leave the conversation, and the eye button next to a N tool calls header (Hide tool calls…) saves the choice for that agent, that project or everywhere. Update both the desktop app and the phone app.
- Why does my pane keep dropping back to the terminal? The CLI asked something only its own interface can show (model picker, plan, trust folder, an Antigravity approval). Answer it and the conversation comes back by itself. A question with options, and a Claude Code or Codex permission prompt, no longer do this: they stay in the thread as a card.
- The Conversation view stayed empty and my Claude agent closed by itself (home folder). Fixed on 2026-10-01: Claude asks "Accessing workspace… Yes, I trust this folder" at every launch in your home folder, with "No, exit" selected, and a message sent at that moment picked it. The view now shows a card The agent asks to work in this folder with Trust this folder, and a message typed meanwhile is held instead of closing the CLI.
- On Windows, a message I typed during "Trust this folder" still closed Claude. Fixed on 2026-10-24: on Windows the app read that dialog as old terminal output, so the message went through and its Enter picked "No, exit". The trust question (and the Bypass permissions warning) is now recognised on Windows as on macOS and Linux: the message is held and the Trust this folder card shows. Update AgentsRoom.
- Can I allow a command from the Conversation view? Yes, with Claude Code and Codex: the card The agent is waiting for your answer shows the question with Allow and Deny. For "Yes, and don't ask again", click More choices in the terminal. If you clicked Terminal yourself, the pane respects that until you switch again.
- How do I copy an agent's answer on my phone to paste it in ChatGPT or Gemini? Tap the Copy answer button under the answer: the whole answer goes to the clipboard and the icon turns into a check. To copy raw terminal output instead, see Terminal Keys and the Agent Console (touch and hold the output).
- Can I copy a code block in one click? Yes, since 2026-11-02. Hover a code block in the answer: a copy button appears in its top right corner, click it and the icon turns into a check. On the phone the button is always shown in the corner of the block; tap it. The same button sits on code blocks of the file preview, backlog tickets and notes.
- The Copy button of a message, or Copy in the selection bar, does nothing (seen on Linux). Fixed on 2026-09-26: when the system refuses the direct clipboard write, the copy now goes through a fallback, as the terminal already did. Update AgentsRoom.
- My selection disappears before I can copy it while the agent is working. Fixed on 2026-09-28: the thread no longer rebuilds its text on every refresh, so a selection stays put while the agent writes. Copy it with Copy in the selection bar, Ctrl+C (Cmd+C on macOS), or the terminal shortcuts Ctrl+Shift+C and Ctrl+Insert, which now work in the Conversation view too.
- Can I make every agent open on the conversation? Settings > Terminal > Conversation view > Always, or per project under Project settings > Terminals.
- I set Conversation view to Always, but my agent switches to the terminal whenever I press Esc to stop it. Fixed on 2026-11-13: Esc pressed anywhere in the window left the conversation and counted as choosing the terminal for that agent, so the default never came back. Now only Esc pressed in the thread itself leaves the view; Esc in the composer interrupts the agent and the conversation stays. Update AgentsRoom.
- I set Conversation view to Always and my Claude agents still opened on the terminal. Fixed on 2026-09-22: the global choice now applies to Claude agents created from the new agent dialog, and the per-project choice is no longer ignored.
- After a handover or /model, I only see the terminal and there is no Conversation button. The floating Conversation button at the top right of the agent pane is never hidden, whatever Simple mode or your Interface elements settings say, fullscreen included. Choosing Always also applies to already-open panes without a manual view choice. The green status dot is an activity indicator, not a view switch.
- The agent asked a question with options and the pane went to the terminal instead of showing the card. Fixed on 2026-09-22: on a slow disk or a long transcript the pane handed itself to the terminal before the question was read back. It now waits for that read, so the card shows in the thread.
- The Conversation view shows only my messages, never the agent's answers (Cursor, Copilot, OpenCode…). Those CLIs do not write a transcript AgentsRoom can read, so the view can only list the messages you sent: the answers are in the terminal. Since 2026-11-13 a line at the bottom of the thread says so (This agent's CLI does not expose a transcript yet: only the messages you sent are listed.), with a Show terminal button. It used to sit at the top of the thread and scrolled out of sight, so the agent looked silent.
- My Antigravity (Gemini) agent's Conversation view only showed my own messages, never its answers. Fixed on 2026-09-30: AgentsRoom now reads the transcript agy writes, answers, tool calls and reasoning included, on the desktop and the phone. Update AgentsRoom; the view fills after the agent's first saved turn.
- My Mistral Vibe agent looks stuck in the terminal. Vibe paints its whole interface full screen, so nothing scrolls until the turn ends. Open the Conversation view (or Show the conversation on the phone): it follows the session log turn by turn.
- The Conversation view lags behind the terminal while the agent writes. Since 2026-10-12, with Claude Code, Codex and Antigravity CLI, the answer appears in the thread as it is written, then turns into the formatted version once the CLI saves it. Since 2026-10-14 it types out smoothly even when the CLI prints a long part at once (the usual case after a tool call), on the desktop and on the phone, where the text arrives every few seconds. Other CLIs still show the answer once saved.
- My message never reached the agent and nothing told me. Since 2026-11-09, when the agent recorded nothing at all a minute after your message, the Conversation view keeps that message at the bottom of the thread with Not received by the agent under it, even if you come back hours later. Click Submit message if the text is still typed in the agent's prompt (it presses Enter once), or Show terminal to see what arrived. Slash commands are never marked. On the phone, a message you sent from it gets the same Not received by the agent line in the Conversation view (with Remove), once the computer confirmed it and the agent, not busy, recorded nothing after it for a minute; it needs a desktop app from 2026-11-09 or later.
- I typed /mcp (or another slash command) in the Conversation view and nothing showed up. Since 2026-11-12 the pane switches to the terminal on its own while the command's menu is open, for every AI provider, so you can drive it with the arrow keys, Enter and Esc. It comes back to the conversation when you close the menu with Esc, when the command's result reaches the transcript, or as soon as you pick a view yourself.
/clearnever switches. The agent no longer shows Working in the sidebar just because a menu is open (Claude Code and other CLIs that report their turns). - Does switching views interrupt the agent? No. The CLI never notices; only what you see changes.
- How do I see my agent's session as a chat instead of the terminal? Click the floating Conversation button at the top right of the agent pane (a message icon, under scroll and fullscreen): the thread replaces the terminal, scrolled to the last turn, with tool calls hidden (Show tool calls in the thread's toolbar brings them back). Click the same button, now Terminal, to go back; the agent is never interrupted. Video: https://youtu.be/hmpwtgJofJg
- Is there a video that shows it? Yes, about a minute, filmed in the real app: https://youtu.be/hmpwtgJofJg
Related
- Mermaid Diagrams: Mermaid blocks drawn inside an agent's answer.
- Read Aloud: the Listen action on an agent answer.
- Needs Input Inbox: the same red dot that heads a waiting question card.
- Message Queue: on the desktop, a "Send all" message shows one block per queued card in this view, each with its own attachments.
- Agent Fork: the same transcript is what a fork copies to another CLI.
- Multi-Provider Support: which CLIs write a readable transcript.
- Remote Agent Control: the phone's console and its dock.
- Agent Reply Language: right-to-left languages are why Auto exists.