feat: v2.5.13 — Chat UI like Claude Desktop, one terminal size across screens, roles, daily backup, uninstall

- Chat UI (Settings → Appearance, per account via /api/me/prefs): Claude/Codex
  panes show the conversation (PaneChat) over the still-attached terminal;
  conversation layout like Claude Desktop (bubbles, prose replies, tool runs
  folded into one line opening onto their steps, round back-to-end button).
- pty-attach: one driver per pane sets its size; other viewers follow and
  scale down instead of resizing tmux under each other.
- Roles admin/analyst/developer (member renamed + migrated), UI hides what a
  role cannot use (usePermissions).
- Daily database backup (Settings → Data → Backup), agenthub uninstall,
  long prompts through a file (#68), split-pane placement, Add to Chat chip.

Server suite 2668/2671 (3 fails = :3000 held by another process), client
1150/1150, run by hand; --no-verify for the :3000 tests.

docs/LANES.md

@@ -391,9 +391,10 @@ The dashboard web UI merges workspaces and runs into a single **Workspace** page
 
 - **No page header.** The page title and the four counters (`lanes`, `running`, `needs you`, `dead`) are gone: the sidebar's workspace list shows every workspace with its own status dot, and the status bar at the bottom of every page counts running and need-you workspaces. `GET /api/lanes` still returns `counts` for other callers.
 - **The sidebar's workspace list picks the workspace** — on every page, below the nav (`client/src/components/WorkspaceTree.tsx`), shaped like Claude Desktop's project list: every workspace on ONE level (no repo grouping, no worktree rows), in your stored order. A row (`WorkspaceRow.tsx`) is a chevron, a status dot (green = active, pulsing while running; amber row = needs you; red = dead or error; grey = idle), the title or folder name and the tool's icon, with `+` (open it for a new session) and `⋯` on hover. Clicking the name opens `/workspace?lane=<id>` and expands the row: the URL is the selection, so a notification link, F5 and the back button all land on the same workspace, and a bare `/workspace` reopens the last one shown (`agenthub.workspace.selected`) or the first. The header has a **tool filter** (shown once workspaces of two tools exist; kept in `agenthub.sidebar.projects` → `tool`, a stored tool no workspace has filters nothing), search and `+` (Add workspace). Search matches workspace names and paths — such a workspace keeps all its sessions — and session names: a workspace whose name does not match still shows when one of its sessions does, with only the matching sessions under it (every list stays mounted, hidden, to load and count). In the collapsed rail the list is a single icon that opens the sidebar. Drag the expanded sidebar's right edge (or focus it and press ←/→) to widen it from 240 px up to 480 px — never more than 40% of the window; the width is kept in `agenthub.sidebar.width` and a double-click on the edge resets it (`client/src/components/Layout.tsx`).
-- **A workspace's sessions** — the chevron expands the row to the sessions the workspace OWNS and has not archived (`WorkspaceSessionList.tsx`: `GET /api/sessions?lane=<id>&archived=0`, the newest 20, re-read when the workspace's status or session moves; which rows are expanded is kept in `agenthub.sidebar.projects` → `expanded`). A live AI tab whose session has no row yet — a tab opened bare from `+`, before its first prompt — is listed at the top as **New session** straight from the run (its session id is known from the start), so a new tab shows in its workspace at once; the row becomes the real session when its first hook lands. The sidebar's live panes follow the Workspace page's own run-list poll (`LIVE_RUNS_EVENT`), since a session in slots 1–9 moves no workspace column. A workspace owns a session its pane held — `bindRunSession` stamps `sessions.lane_id` from the pane's run, first writer wins, a nested `claude -p` excluded — and lists nothing else: a `claude` typed into a terminal in the same folder, or history from before the workspace existed, belongs to no workspace and is found on the Sessions page. Sessions older than this ownership column are not guessed: only those `dashboard_runs` still named were backfilled. A session started by a tool with no hooks (Codex without its hooks, any catalog tool) is never stamped. A row's dot is the session's state (`sessionDot`: amber waiting for you, red failed, green a live pane, hollow at rest); double-click renames it (`PATCH {name}`), and its hover button **archives** it (`PATCH {archived: true}` — hidden from the workspace, nothing deleted; the home lists the archived ones folded with **Unarchive**). A filled dot marks a session that still has a live pane (a `GET /api/run` handle carrying its session id — every pane the dashboard starts carries `AGENTHUB_RUN_ID=<its tmux name>`, the hook handler forwards it as `run_id`, and `bindRunSession` in `server/routes/hooks.js` records the hook's session on that run: the first session always, afterwards — for a Claude pane — only a `SessionStart` that is not a fresh `startup` (`/clear`, `/resume`), so a `claude -p` the agent runs inside the pane never takes it over; the rule is Claude-only, and a Codex or Antigravity pane follows every new session): clicking it opens `/workspace?lane=<id>&run=<runId>`, which ATTACHES to that tmux session (`attachRequest` on `LaneConsolePane`) — it starts nothing and resumes nothing. The session opens on its own tab (the tab of its tmux slot): in the pane already showing it (focused), else in the focused pane; **Ctrl/Cmd+click** opens it in a split beside the focused pane (see **Split panes** below). Any other session opens in its workspace the way Claude Desktop opens an old one: `/workspace?lane=<id>&session=<id>` shows its conversation, read-only (`SessionReplay.tsx`, the console hidden — never unmounted — behind it), with a prompt box under it. Opening it resumes nothing; **sending** a message resumes it (`POST /api/lanes/:id/start {slot, resumeSessionId, prompt}` in the first free pane slot, on the tool the session ran on) and opens that pane — a resume re-reads the whole transcript into context, so it waits for that explicit send. The session's analysis page (`/sessions/<id>`: agents, events, cost, transcript) is the **Analyst** button in the session view's right panel, beside Files and Changes (disabled while the pane's run has reported no session yet).
+- **A workspace's sessions** — the chevron expands the row to the sessions the workspace OWNS and has not archived (`WorkspaceSessionList.tsx`: `GET /api/sessions?lane=<id>&archived=0`, the newest 20, re-read when the workspace's status or session moves; which rows are expanded is kept in `agenthub.sidebar.projects` → `expanded`). A live AI tab whose session has no row yet — a tab opened bare from `+`, before its first prompt — is listed at the top as **New session** straight from the run (its session id is known from the start), so a new tab shows in its workspace at once; the row becomes the real session when its first hook lands. The sidebar's live panes follow the Workspace page's own run-list poll (`LIVE_RUNS_EVENT`), since a session in slots 1–9 moves no workspace column. A workspace owns a session its pane held — `bindRunSession` stamps `sessions.lane_id` from the pane's run, first writer wins, a nested `claude -p` excluded — and lists nothing else: a `claude` typed into a terminal in the same folder, or history from before the workspace existed, belongs to no workspace and is found on the Sessions page. Sessions older than this ownership column are not guessed: only those `dashboard_runs` still named were backfilled. A session started by a tool with no hooks (Codex without its hooks, any catalog tool) is never stamped. A row's dot is the session's state (`sessionDot`: amber waiting for you, red failed, green a live pane, hollow at rest); double-click renames it (`PATCH {name}`), and its hover button **archives** it (`PATCH {archived: true}` — hidden from the workspace, nothing deleted; the home lists the archived ones folded with **Unarchive**). A filled dot marks a session that still has a live pane (a `GET /api/run` handle carrying its session id — every pane the dashboard starts carries `AGENTHUB_RUN_ID=<its tmux name>`, the hook handler forwards it as `run_id`, and `bindRunSession` in `server/routes/hooks.js` records the hook's session on that run: the first session always, afterwards — for a Claude pane — only a `SessionStart` that is not a fresh `startup` (`/clear`, `/resume`), so a `claude -p` the agent runs inside the pane never takes it over; the rule is Claude-only, and a Codex or Antigravity pane follows every new session): clicking it opens `/workspace?lane=<id>&run=<runId>`, which ATTACHES to that tmux session (`attachRequest` on `LaneConsolePane`) — it starts nothing and resumes nothing. The session opens on its own tab (the tab of its tmux slot): in the pane already showing it (focused), else in the focused pane; **Ctrl/Cmd+click** opens it in a split in the tab on screen (see **Split panes** below). Any other session opens in its workspace the way Claude Desktop opens an old one: `/workspace?lane=<id>&session=<id>` shows its conversation, read-only (`SessionReplay.tsx`, the console hidden — never unmounted — behind it), with a prompt box under it. Opening it resumes nothing; **sending** a message resumes it (`POST /api/lanes/:id/start {slot, resumeSessionId, prompt}` in the first free pane slot, on the tool the session ran on) and opens that pane — a resume re-reads the whole transcript into context, so it waits for that explicit send. The session's analysis page (`/sessions/<id>`: agents, events, cost, transcript) is the **Analyst** button in the session view's right panel, beside Files and Changes (disabled while the pane's run has reported no session yet).
 - **Row menu** — right-click a row, or its `⋯` button: Rename, the Model (AI Proxy) select, New workspace here…, Copy path, Reset worktree… (managed only) and Delete workspace…, each the call the rest of the UI already makes. Delete is record-only exactly as before (see "Removing a workspace").
 - **Right-click menus** — every item that has actions opens them on a right-click too, in one shell (`client/src/components/ContextMenu.tsx`: placed at the pointer, kept inside the viewport, closed by Escape, a click outside or an item). The buttons stay; the menu repeats what they do and nothing more. A session row — in the sidebar, the home's Recents and the archived fold (`lanes/SessionMenu.tsx`) — offers Open, Open in split (live), Rename and Archive (sidebar), Unarchive (archived), Session details, Copy session ID and Close tab (live); the sidebar's **New session** row Open, Open in split and Close tab. A console tab offers Open, Open in split, Session details, Copy session ID and Close tab; a pane header (split view) Show <session> here, Split right/down with a new terminal and Close pane. In the Changes panel a changed file (overview row or review header) offers Open, Stage/Unstage, Discard — two clicks, as on its trash button — or the conflict's Keep mine / Take theirs / Mark resolved, and Copy relative path; a Files tree entry Open and Copy relative path; a History commit View commit, Copy commit SHA and Copy commit message. The home's title opens the row menu, and a Context file or extra folder offers Copy path and Remove. Outside the workspace the same shell serves the Sessions table, the Dashboard's agent cards and recent events, the Activity feed and Workflow runs (`components/SessionRowMenu.tsx`: Open session details, Open in its workspace when it has one, Copy session ID, Copy folder path), an attached prompt image (View / Remove), the managed workspace card (Reset), every Settings list (Git credentials, AI Proxy, Pricing, alert rules, webhooks, remote sources, AI tools) and every Claude Code / Codex config list (skills, agents, commands, output styles and memory files via `FileItemMenu` in `components/config/MdItemList.tsx`; plugins, MCP servers, marketplaces, auth profiles). A delete or remove there takes the button's own confirm — a modal, or two clicks. Text areas (the terminal, a conversation, a diff) keep the browser's own menu. The shell stops the menu's clicks from reaching the card it was opened from.
+- **Chat view of a live pane** — with **Settings → Appearance → Chat UI** on (`ChatUiSettings.tsx`, one choice for every pane, saved per ACCOUNT on the server: `GET/PUT /api/me/prefs`, key `agenthub.chatUi`, `client/src/lib/chatUi.ts`, so each user of a shared dashboard keeps their own on any browser), a Claude or Codex pane whose session is known shows a chat instead of its terminal (`client/src/components/run/LaneConsolePane.tsx`). Chat (`client/src/components/run/PaneChat.tsx`) shows the session's conversation the way Claude Desktop does — the shared `ConversationView` in its `fill` layout: one centred column, your messages as bubbles, the reply as plain prose, every run of tool calls and thinking folded into one line named by what it did ("Ran 3 commands, edited a file ›", `workLabel`) that opens onto a framed list of its steps — each titled by its own description, the call in a capped scroll box, its output one click further — and a round ↓ back to the end — above a prompt box. It lies OVER the terminal, which stays mounted and attached (the console never unmounts a terminal); a message is sent through that terminal as a bracketed paste and Enter (`submitToRun` in `client/src/lib/panePaste.ts`), exactly as if typed, so no new route or server write exists for it. A permission prompt or a menu still needs the terminal — turn Chat UI off to answer it. The ended-session replay and the Analyst page's conversation use the same layout.
 - **The workspace home** — `/workspace?lane=<id>` opens on the workspace's home (`client/src/components/lanes/WorkspaceHome.tsx`), shaped like a Claude Desktop project page: the name (rename from its `⋯` menu, which is the sidebar row menu) with the repository it belongs to under it (root, the main worktree's branch, the worktree count, from `GET /api/projects` — the facts Settings → Projects used to show), a prompt box — the one place a session starts WITH a prompt (a pane has no run form; the session view's tab bar `+` only starts a bare CLI or a shell) — whose fields run in order **AI** (the session's own tool: every installed, enabled one, the workspace's by default), **AI Proxy** (Native or a saved profile; Native alone, disabled, for a tool that cannot use one), **Model** (the tool's own list, or on a router that router's models), **Permission** (Claude's permission mode; Codex's sandbox and approval; a catalog tool's per-session bypass switch) and **Effort** (Claude and Codex), whose half-typed text is kept per workspace in `agenthub.workspace.draft.<lane id>` (localStorage, so it survives leaving the page or switching workspace; cleared once sent — attached images are not kept), and whose **Start** opens a NEW session in the first slot with no live run (0–9, `POST /api/lanes/:id/start {slot}`; all ten busy is refused) and then shows it in a tab of its own, and **Recents** — the workspace's own sessions (`?lane=<id>`) with their cost and time, a live one opening its pane and any other its conversation (`&session=`), exactly like the sidebar. The transcript page (`/sessions/<id>`) of a Claude session started in a workspace's own folder carries an explicit **Resume** (`client/src/components/lanes/SessionResumeButton.tsx`, the one place that resumes) and beside it **Fork**, which resumes the history into a NEW session id (`{forkSession: true}` → `--fork-session`, the original untouched, offered even while the original has a live pane): it warns that a resume re-reads the whole transcript into context, re-reads the live panes, then starts it in the workspace's first free pane (`POST /api/lanes/:id/start {slot, resumeSessionId}`) and opens it. A session from a SUBFOLDER gets no Resume — the pane starts in the workspace's folder and Claude finds a session by the folder it ran in — and a session that still has a live pane shows **Open pane** instead. On the right sit the workspace's own context: **Instructions** (appended to every new session's system prompt), **Memory** (read-only: the folder's CLAUDE.md / AGENTS.md family and Claude's auto memory), **Context** (uploaded files, ≤ 10 MB each, stored by AgentHub) and **Folder** (the workspace's own folder plus extra ones, with the repo's untracked worktrees suggested). Only Claude and Codex panes can take them (`--add-dir`, `--append-system-prompt-file=` / `-c developer_instructions=`); for any other tool the page says so and its panes start without them. See `docs/API.md` → Workspace context. The home HIDES the session view with CSS — the console never unmounts behind it.
 - **A session in its own worktree** — Claude Desktop's worktree toggle: the row under the home's prompt box has a **Local / New worktree** select (Claude workspaces in a git repo). Claude Code itself makes a worktree only when started with `--worktree` or when asked mid-session — and a worktree it enters mid-session is invisible to AgentHub, which reads a session's folder once, at its start, and the new session's pane runs `claude --worktree=<name>`, so CLAUDE CODE makes `<repo>/.claude/worktrees/<name>` on branch `worktree-<name>`, copies `.worktreeinclude`, runs your `WorktreeCreate` hook, and on exit removes a worktree with no changes (or asks). AgentHub adds `/.claude/worktrees/` to the repo's `info/exclude` (Claude does not, and the main repo would list it). The session stays this workspace's own — listed with a branch icon and the worktree's name — and the session view's Changes panel works in ITS worktree (every git route with `?session=`, resolved from the session row: owned by the workspace, registered by `git worktree list`; `ENOWORKTREE` otherwise, never the main folder). Resume and Fork start in that worktree. **Archive** of a worktree session with no live pane asks first and removes the worktree like Claude Desktop — `git worktree remove` without force (git refuses unsaved work, and then nothing is archived) and `git branch -d` (unmerged work keeps its branch); a lock held by a live process refuses, a stale one is cleared. The workspace's own folder is never removed.
 - **The session view** — `/workspace?lane=<id>&run=<runId>` (a live session picked in the sidebar or Recents, or one just started) shows the console's tabs and the Changes panel, with that run's tab active. The sidebar's workspace row always opens the workspace's home, live tabs or not (a live tab opens from its session row); the **Home** button at the left end of the tab bar opens the home of a workspace whose tabs stay running. Every workspace keeps its own tabs, panes and sessions: another workspace's tab is never shown. A browser notification for a workspace with a live pane opens it here directly.
@@ -407,9 +408,9 @@ The dashboard web UI merges workspaces and runs into a single **Workspace** page
   Keyboard: the terminal keeps Tab and Shift+Tab (`claude` cycles its permission mode on Shift+Tab), so **Ctrl+M** toggles *Tab moves focus* — VS Code's way out of its terminal — and Tab then leaves the pane; **Cmd+F** (macOS) / **Ctrl+Shift+F** opens a find bar. URLs open in a new tab; a selection tmux copies (OSC 52) lands in the browser clipboard, and that path is write-only — nothing in the pane can read your clipboard. `agenthub.terminal.screenReader` = `"1"` in `localStorage` turns on xterm's screen-reader mode. While the socket is down a **Reconnecting…** overlay says keystrokes are not reaching the pane; it re-attaches by itself. In the session view, outside a terminal or a text field, `Alt+1`–`Alt+4` focuses pane 1–4, `Alt+\` splits the focused pane right with a new terminal, and `Alt+W` closes the focused pane (its session stays a tab).
 - **Clipboard in a pane** — the workspace's tmux session is started with the graphical session's own `DISPLAY`/`WAYLAND_DISPLAY`/`XAUTHORITY`/`XDG_RUNTIME_DIR` (read from `systemctl --user show-environment`, this process's own values winning; `server/lib/desktop-env.js`). The dashboard normally runs as a systemd *user* service, which has none of them, so a pane it started had no clipboard at all and `claude` answered "no image found in clipboard" on every image paste while the same CLI pasted fine in a terminal. Only those four names are forwarded, and only into panes this dashboard spawns — an already-running pane keeps the environment it was started with, so it needs a restart to gain one.
 - **Scrollbar in a pane** — every pane gets tmux's `mouse on` and `pane-scrollbars on` with a visible style (`pane-scrollbars-style fg=brightwhite,bg=black,width=1`, `enableMouse` in `server/lib/tmux.js`; tmux 3.7+ — one column, since tmux 3.7c reserves `width` columns but paints only the first and a wider bar left a column of stale cells that read as a second scrollbar). tmux keeps no history and draws no scrollbar on the alternate screen, so a `claude` pane under `"tui": "fullscreen"` (`~/.claude/settings.json`) scrolls inside Claude's own UI instead. AgentHub no longer forces it inline (`CLAUDE_CODE_DISABLE_ALTERNATE_SCREEN=1`): inline, every time the pane narrowed tmux re-wrapped Claude's full-width rules and pushed lines into history that its redraw could not clear, duplicating the banner and transcript. A pane started before this change keeps inline mode until it is restarted. Every pane's CLI (and a Terminal tab's shell) also starts only once a client is attached — 2 s at most — so nothing is drawn at tmux's 80×24 birth size and re-wrapped on the attach (`WAIT_FOR_CLIENT` in `server/lib/pty-run.js`, issue #55).
-- **Tabs** — the session view's console is a tab bar (`client/src/components/run/ConsoleTabs.tsx`) over the workspace's live tmux sessions — at most ten, its slots 0–9: slot 0 is the workspace's `agenthub-lane-<id>` (its `run_id`), slots 1–9 are `agenthub-lane-<id>-<slot>`. Every tab is a **combo**: a group of one to four split panes, each session in exactly one tab (`PaneGroups` in `client/src/lib/paneLayout.ts`). A one-pane tab shows its AI tool's icon and name (or **Terminal**); a combo tab shows every pane's icon and name, and the most urgent state dot. The active tab is the one on screen and its focused pane is the URL's `?run=`, so the Changes panel and Analyst follow it. A click shows a tab; **Ctrl/Cmd+click** on a one-pane tab or a `+` item brings it into the tab on screen, split to the right (a full tab — four panes — opens it as a tab of its own instead), and a one-pane tab dragged onto a pane joins that tab there. Any tab drags along the bar to reorder it; a pane's header dragged onto the bar takes that pane out into a tab of its own at that place. Dropped on the MIDDLE of another tab (it highlights), a tab — or a pane's header — joins that tab instead, in a fixed order: the second pane goes to the right (left | right), the third under the right pane, the fourth under the left pane (2×2); a drop that would pass four panes reorders instead (`joinGroup`). Every live session stays mounted and those of other tabs are hidden with CSS, so switching tabs never drops a terminal. A tab's **×** stops every session in it (`DELETE /api/run/<runId>`, after a confirm when one is an AI tool); with no tab left it moves to the home. The **+** menu opens a new tab in the first free slot, which the server picks (`slot: "auto"`, under the workspace lock): **New terminal** (your own default shell in the workspace folder — `POST /api/lanes/:id/start {slot, shell: true}`, recorded as tool `shell`; it is not an agent, so the workspace's `run_id`/`status` are left alone), each installed, enabled AI tool (started bare, on its default model, no prompt), and **Agent settings…** (Settings → Agents). With ten sessions open **+** is disabled. EVERY tab is bound to the sidebar's selection. A tab has no header of its own (no title, no **Active runs** list, no **New run**): other sessions are opened from the sidebar or the home's Recents. (The old fixed 1/2/4 split layout and its `agenthub.workspace.splitView` key are gone; **Split panes** replaces them.)
+- **Tabs** — the session view's console is a tab bar (`client/src/components/run/ConsoleTabs.tsx`) over the workspace's live tmux sessions — at most ten, its slots 0–9: slot 0 is the workspace's `agenthub-lane-<id>` (its `run_id`), slots 1–9 are `agenthub-lane-<id>-<slot>`. Every tab is a **combo**: a group of one to four split panes, each session in exactly one tab (`PaneGroups` in `client/src/lib/paneLayout.ts`). A one-pane tab shows its AI tool's icon and name (or **Terminal**); a combo tab shows every pane's icon and name, and the most urgent state dot. The active tab is the one on screen and its focused pane is the URL's `?run=`, so the Changes panel and Analyst follow it. A click shows a tab; **Ctrl/Cmd+click** on a one-pane tab or a `+` item brings it into the tab on screen, in the same order as a join below (a full tab — four panes — opens it as a tab of its own instead), and a one-pane tab dragged onto a pane joins that tab there. Any tab drags along the bar to reorder it; a pane's header dragged onto the bar takes that pane out into a tab of its own at that place. Dropped on the MIDDLE of another tab (it highlights), a tab — or a pane's header — joins that tab instead, in a fixed order: the second pane goes to the right (left | right), the third under the right pane, the fourth under the left pane (2×2) — the new pane always splits the BIGGEST one by the tree's shape (dragged dividers ignored, a tie goes to the later pane), so a three-pane tab of any shape fills its one missing quarter; a drop that would pass four panes reorders instead (`joinGroup`). Every live session stays mounted and those of other tabs are hidden with CSS, so switching tabs never drops a terminal. A tab's **×** stops every session in it (`DELETE /api/run/<runId>`, after a confirm when one is an AI tool); with no tab left it moves to the home. The **+** menu opens a new tab in the first free slot, which the server picks (`slot: "auto"`, under the workspace lock): **New terminal** (your own default shell in the workspace folder — `POST /api/lanes/:id/start {slot, shell: true}`, recorded as tool `shell`; it is not an agent, so the workspace's `run_id`/`status` are left alone), each installed, enabled AI tool (started bare, on its default model, no prompt), and **Agent settings…** (Settings → Agents). With ten sessions open **+** is disabled. EVERY tab is bound to the sidebar's selection. A tab has no header of its own (no title, no **Active runs** list, no **New run**): other sessions are opened from the sidebar or the home's Recents. (The old fixed 1/2/4 split layout and its `agenthub.workspace.splitView` key are gone; **Split panes** replaces them.)
 
-- **Split panes** — the console splits like VS Code (`client/src/components/run/PaneGrid.tsx`, model in `client/src/lib/paneLayout.ts`): one binary tree of splits PER TAB, each side by side or stacked at a ratio, whose leaves are the workspace's slots — at most four panes in a tab, a session never shown twice. **Ctrl/Cmd+click** a one-pane tab, a `+` item or a sidebar session row brings it into the tab on screen, to the right of the focused pane (the intent rides on the navigation's state, never in the URL); with more than one pane each gets a slim header: **drag** it (or a tab) onto another pane — its edge splits there, its middle swaps the two —, its **▾** shows another live session in it (swapping with the pane that showed it), **Split right / Split down** puts a not-shown session or a **New terminal** beside it, its **⤡** takes the pane out of this tab into a tab of its own (its session keeps running), and its **×** (also in the header's right-click menu) stops just that pane's session — the same `DELETE /api/run/<runId>` and AI-tool confirm as a tab's **×** — without taking it out first. A session dropped or swapped in from another tab leaves that tab. Dividers drag (or move by arrow keys) between 10% and 90%. Clicking in (or tabbing into) a pane focuses it, `?run=` follows — so the right panel, Analyst and the sidebar read the focused session — and the keyboard goes with it: only the focused pane's terminal takes it when it appears. A pane closes when its terminal reports that its session ended (exited, closed from another browser); the run list itself only prunes a remembered layout on a workspace's first read, and a pane opened here whose session never got listed — one empty read, which the server returns on any tmux error, never wipes a split. A session ending while the home or a replay is shown only closes its pane; the URL stays. The tabs and their layouts are a viewer preference kept per workspace in `localStorage` (`agenthub.workspace.paneLayout`, `{groups, active}`; a stored pre-tab single layout reads as one tab), never on the server. Every pane is an absolutely placed sibling keyed by its slot, so splitting, swapping or resizing never re-parents — and so never remounts — a live terminal; the session view itself fills the page edge to edge, its tab bar and the right panel's activity bar one header strip.
+- **Split panes** — the console splits like VS Code (`client/src/components/run/PaneGrid.tsx`, model in `client/src/lib/paneLayout.ts`): one binary tree of splits PER TAB, each side by side or stacked at a ratio, whose leaves are the workspace's slots — at most four panes in a tab, a session never shown twice. **Ctrl/Cmd+click** a one-pane tab, a `+` item or a sidebar session row brings it into the tab on screen at the 2×2 grid's next place — the same order as a tab join, whichever pane is focused (the intent rides on the navigation's state, never in the URL); with more than one pane each gets a slim header: **drag** it (or a tab) onto another pane — its edge splits there, its middle swaps the two —, its **▾** shows another live session in it (swapping with the pane that showed it), **Split right / Split down** puts a not-shown session or a **New terminal** beside it, its **⤡** takes the pane out of this tab into a tab of its own (its session keeps running), and its **×** (also in the header's right-click menu) stops just that pane's session — the same `DELETE /api/run/<runId>` and AI-tool confirm as a tab's **×** — without taking it out first. A session dropped or swapped in from another tab leaves that tab. Dividers drag (or move by arrow keys) between 10% and 90%. Clicking in (or tabbing into) a pane focuses it, `?run=` follows — so the right panel, Analyst and the sidebar read the focused session — and the keyboard goes with it: only the focused pane's terminal takes it when it appears. A pane closes when its terminal reports that its session ended (exited, closed from another browser); the run list itself only prunes a remembered layout on a workspace's first read, and a pane opened here whose session never got listed — one empty read, which the server returns on any tmux error, never wipes a split. A session ending while the home or a replay is shown only closes its pane; the URL stays. The tabs and their layouts are a viewer preference kept per workspace in `localStorage` (`agenthub.workspace.paneLayout`, `{groups, active}`; a stored pre-tab single layout reads as one tab), never on the server. Every pane is an absolutely placed sibling keyed by its slot, so splitting, swapping or resizing never re-parents — and so never remounts — a live terminal; the session view itself fills the page edge to edge, its tab bar and the right panel's activity bar one header strip.
 - **Workspace grid** — one card per workspace, 1 column, 2 at `md`, 3 at `xl`. Each card carries the workspace id, liveness dot and status, title, declared stage and time-on-stage, the `auto:` chip when detection leads, the kind and CI tags, the working-copy facts from `GET /api/lanes/:id/git`, and the action row. The needs-you message (`needs_action`) is on the workspace list tile only — the detail card no longer repeats it as a banner.
 
 Run history is per workspace, queryable via `GET /api/run/history?laneId=<n>`.
@@ -693,7 +694,7 @@ reads the workspace's git surface in five modes:
   user presses Enter in the pane; with no pane of the workspace open the box
   says so and keeps the text.
   In the file editor, a text selection shows Cursor's **Add to Chat** chip
-  above it, which pastes `@<path>#L<from>-<to>` (Claude Code's line-range
+  at the end of its first line (inline, covering no code), which pastes `@<path>#L<from>-<to>` (Claude Code's line-range
   mention; `#L<n>` for one line — without the `L` Claude Code attaches the
   whole file) the same way. Other tools (Codex, …) get the same text as a
   plain hint.
@@ -1809,7 +1810,7 @@ agenthub stage <stage> [--evidence "..."]         # Report the current stage
 
 ## Workspaces on any AI tool
 
-A workspace can run any AI coding CLI in the AI Tools catalog (`server/data/ai-tools/*.json` — nine built in: Claude Code, Codex, Antigravity, GitHub Copilot CLI, OpenCode, Cursor CLI (`cursor-agent`), Grok Build (`grok`), Kimi Code (`kimi`) and Oh My Pi —, plus any `*.json` in `DASHBOARD_AI_TOOLS_DIR`, which replaces a built-in file with the same `id` but may not set `launcher`). Settings → Agents → **AI tools** (`/settings/agents`; the old `/settings#ai-tools` redirects there) lists what is installed (found on PATH; **Refresh** re-reads the login shell's PATH first) with an enable switch, **Set default** and **Update** (for every tool whose catalog file names an updater — no version lookup, the updater itself reports "up to date"), and, folded behind a disclosure, what is available to install with a homepage link. The Add-workspace modal shows the chosen tool as one button (the default until changed); clicking it lists every installed, enabled tool as buttons to pick from; `agenthub workspace add --tool <id>` does the same from a terminal. The run form's **Model** picker lists the workspace tool's own models (`GET /api/ai-tools/:id/models`; Claude, Codex, and any catalog tool whose file declares `model: { flag }` — the id is validated and passed as `<flag> <id>`), plus **Custom…**, and starts on the tool's default model when one is set.
+A workspace can run any AI coding CLI in the AI Tools catalog (`server/data/ai-tools/*.json` — nine built in: Claude Code, Codex, Antigravity, GitHub Copilot CLI, OpenCode, Cursor CLI (`cursor-agent`), Grok Build (`grok`), Kimi Code (`kimi`) and Oh My Pi —, plus any `*.json` in `DASHBOARD_AI_TOOLS_DIR`, which replaces a built-in file with the same `id` but may not set `launcher`). Settings → Agents → **AI tools** (`/settings/agents`; the old `/settings#ai-tools` redirects there) lists what is installed (found on PATH; **Refresh** re-reads the login shell's PATH first) with an enable switch, **Set default** and **Update** (for every tool whose catalog file names an updater — no version lookup, the updater itself reports "up to date"), and, folded behind a disclosure, what is available to install with a homepage link. Each installed, enabled tool's own settings (`/settings/agents/<id>`) are tabs on that page — **All tools** · Claude Code · Codex · … — rather than items in the left nav, and a click on a tool's row (or its name) opens its tab. The Add-workspace modal shows the chosen tool as one button (the default until changed); clicking it lists every installed, enabled tool as buttons to pick from; `agenthub workspace add --tool <id>` does the same from a terminal. The run form's **Model** picker lists the workspace tool's own models (`GET /api/ai-tools/:id/models`; Claude, Codex, and any catalog tool whose file declares `model: { flag }` — the id is validated and passed as `<flag> <id>`), plus **Custom…**, and starts on the tool's default model when one is set.
 
 A catalog file: