feat(workspace): AI tool per session, one place to start a session, ended sessions open like Claude Desktop

- A session picks its own AI tool: `tool` on POST /api/lanes/:id/start
  (a catalog id, known + enabled, else 400 EBADTOOL/EDISABLED); a resume
  keeps the tool its session ran on (`sessions.tool`). The workspace's
  `lanes.tool` is now only the default.
- The workspace home's prompt box is the one place a session starts. Its
  fields run in order: AI → AI Router (Native or a profile) → Model (the
  tool's own list, or the router's models) → Permission (Claude mode /
  Codex sandbox+approval / catalog bypass) → Effort.
- The pane's run form (RunSetup) is gone: New run, a single pane's exit and
  an empty split pane's New session all go to the home. RunSetup.tsx keeps
  PromptEditor, CwdAutocomplete and ModelPicker (new `choices` prop).
- The tool icon moved from the sidebar's workspace row to each session row
  (right edge, `session.tool`); the split-pane header shows the run's tool.
- An ended session opens in its workspace (`&session=`, SessionReplay.tsx):
  its conversation read-only plus a prompt box; only a SENT message resumes
  it (resumeSessionId + prompt, first free slot). The console is only
  hidden behind it.
- Analyst button beside Files/Changes in the right panel opens
  /sessions/:id for the opened session.
- Gemini CLI ships its own icon (client/public/ai-tools/gemini.svg, from
  zonalogo.com).
- RouterPicker always shows (Native disabled for tools without router
  support); useAiRouters() exported.
- Tests: server start-with-tool cases; SessionReplay, home field order/tool/
  router models, empty pane, Analyst; dropped the cwd-field suites
  (Run.defaultCwd, Workspace.laneCwd). Docs: CLAUDE.md rules, API.md,
  LANES.md, README, ARCHITECTURE, INSTALL.

docs/API.md

@@ -150,8 +150,8 @@ it a `cwd` nested inside another workspace returns that parent workspace (`creat
 false`); with it the nested directory gets a workspace of its own. The Add-workspace
 modal sends it, and says so when the directory already has a workspace. An id no template defines returns `400 EBADPIPELINE`.
 
-`tool` (`"claude"` or `"codex"`, default `"claude"`) is the CLI this workspace's
-runs will spawn. Immutable once the workspace is created; an attempt to update it on
+`tool` (an AI Tools catalog id, default `"claude"`) is the CLI this workspace's
+sessions start on unless a start names another (`POST /api/lanes/:id/start` `tool`). Immutable once the workspace is created; an attempt to update it on
 an existing workspace returns `400 EBADTOOL`. The tool choice appears as an immutable
 badge on the workspace card (Codex workspaces only).
 
@@ -228,8 +228,8 @@ existing `lane_update` message when the workspace becomes `idle` or `failed`.
 }
 ```
 
-`tool` (`"claude"` or `"codex"`, default `"claude"`) is the CLI this workspace's
-runs will spawn. Immutable once the workspace is created; an attempt to update it on
+`tool` (an AI Tools catalog id, default `"claude"`) is the CLI this workspace's
+sessions start on unless a start names another (`POST /api/lanes/:id/start` `tool`). Immutable once the workspace is created; an attempt to update it on
 an existing workspace returns `400 EBADTOOL`.
 
 `sourceRepo` must exist, be absolute, and be a git repository with at least
@@ -266,7 +266,11 @@ Starts a new run in the workspace's working directory, or attaches an existing i
 }
 ```
 
-All fields are optional. The tool (CLI invoked) comes from the workspace itself, never the request — **a client cannot override a workspace's tool**. If the workspace is a Codex workspace, three fields control Codex-specific behavior:
+All fields are optional.
+
+- **`tool`** — the AI tool THIS session runs on, an AI Tools catalog id (only an id; the command, args and env still come from the catalog file). Omitted = the workspace's own tool. It must be known (`400 EBADTOOL`) and enabled (`400 EDISABLED`); the workspace's own tool is never re-checked, so a workspace on a tool disabled since keeps starting when `tool` is omitted. A resume (`resumeSessionId`, or `resume`) ignores `tool` and keeps the tool its session ran on (`sessions.tool`). The workspace's own `tool` column is unchanged. The run is recorded with its tool (`dashboard_runs.tool`, the run handle's `tool`).
+
+When the session's tool is Codex, three fields control Codex-specific behavior:
 
 - **`sandbox`** — one of `read-only`, `workspace-write`, or `danger-full-access`, or omitted/empty for no sandbox. Passed to `codex -s <value>`.
 - **`approval`** — one of `on-request` or `never`, or omitted/empty for no approval prompt. Passed to `codex -a <value>`.

docs/LANES.md

@@ -87,20 +87,20 @@ terminal with `agenthub lanes add --pipeline <id>`. *Model endpoint* is the one
 per-workspace extra the form still asks for, and it sits in the form itself rather
 than behind a disclosure — a disclosure around a single field only hid it.
 
-A workspace has no AI Router of its own: each NEW session picks one. The **AI Router** select beside the model picker — in the workspace home's prompt box and in a pane's run form — lists the profiles saved in Settings › AI Router (9Router, OpenRouter, a self-hosted gateway) plus **Native** (the vendor's own API); it is hidden when only Native exists or the workspace's tool cannot use a router (only Claude and Codex can), and it remembers the last pick (`agenthub.session.router`). The start sends `router: "<name>"`; a Claude pane then runs with `--settings=<data dir>/router-settings/<name>.json`, which outranks the workspace's own settings, and a Codex pane with `-p <name>` plus its key through tmux `-e`. So two sessions of one workspace can run on two routers, a worktree session gets its router too, and switching never touches a running session. A resume goes back to the router its session last ran on (`dashboard_runs.router`). Editing a profile in Settings rewrites those files (a rotated key reaches live Claude sessions); deleting it removes them. Older builds wrote a workspace's router into its `.claude/settings.local.json`; every server start takes those eight keys back out. See `docs/API.md` § AI Router profiles.
+A workspace has no AI Router of its own: each NEW session picks one. The **AI Router** select in the workspace home's prompt box lists the profiles saved in Settings › AI Router (9Router, OpenRouter, a self-hosted gateway) plus **Native** (the vendor's own API); it shows Native alone, disabled, when the session's AI tool cannot use a router (only Claude and Codex can), and it remembers the last pick (`agenthub.session.router`). The start sends `router: "<name>"`; a Claude pane then runs with `--settings=<data dir>/router-settings/<name>.json`, which outranks the workspace's own settings, and a Codex pane with `-p <name>` plus its key through tmux `-e`. So two sessions of one workspace can run on two routers, a worktree session gets its router too, and switching never touches a running session. A resume goes back to the router its session last ran on (`dashboard_runs.router`). Editing a profile in Settings rewrites those files (a rotated key reaches live Claude sessions); deleting it removes them. Older builds wrote a workspace's router into its `.claude/settings.local.json`; every server start takes those eight keys back out. See `docs/API.md` § AI Router profiles.
 
 Both modes' path field has a **Browse** button next to it, opening a small folder browser (`GET /api/lanes/browse?path=<abs>`) instead of a native OS picker — a browser cannot hand a web page an absolute filesystem path from a native dialog, so this dashboard (local-first, server and browser on the same machine) lists directories server-side instead: click a subfolder to descend, ".." to go up, "Select this folder" to fill the path field. Git repos are marked in the listing.
 
 ## Workspace tool: Claude or Codex
 
-A workspace is driven by a tool: **Claude** (default) or **Codex**, chosen in the "+ Add workspace" modal and immutable once the workspace exists. A workspace's tool determines which CLI is spawned when a run starts.
+A workspace has a default tool: **Claude** (default) or **Codex** (or any AI Tools id), chosen in the "+ Add workspace" modal and immutable once the workspace exists. Each NEW session picks its own in the workspace home's prompt box — the **AI** select, first of its fields (AI → AI Router → Model → Permission → Effort), lists every installed, enabled tool and starts on the workspace's — and `POST /api/lanes/:id/start` takes it as `tool`; a resume keeps the tool its session ran on (`sessions.tool`). The sidebar draws each session's tool icon at the right of its row.
 
 - **`claude` (default)** — `claude` binary is invoked; the session's hooks, messages, and tool calls flow through the dashboard. Claude workspaces render Sessions, Analytics, cost, and stage-detection badges; liveness is tracked by the Claude Code session.
-- **`codex` (experimental)** — `codex` binary is invoked instead. The Run Setup panel shows fields for model, sandbox, and approval mode instead of the Claude session picker, and offers "Resume last Codex run" instead of picking a session. Resume uses `codex resume --last`. Codex workspaces carry **no pipeline**: no stage chip, no time-on-stage, no pipeline or feature picker and no PipelineMap, and nothing infers or advances their stage. They also get no Sessions/Analytics/cost. (The console pre-fills nothing into the prompt box, for either tool.)
+- **`codex` (experimental)** — `codex` binary is invoked instead. The home's prompt box shows Sandbox and Approval in place of Claude's permission mode. Codex workspaces carry **no pipeline**: no stage chip, no time-on-stage, no pipeline or feature picker and no PipelineMap, and nothing infers or advances their stage. They also get no Sessions/Analytics/cost. (The console pre-fills nothing into the prompt box, for either tool.)
 
 ### How Codex arguments map
 
-The Run Setup panel's fields map directly onto `codex` command-line arguments:
+The prompt box's fields map directly onto `codex` command-line arguments:
 
 - **Model** → `codex -m <model>` (e.g. `codex -m claude-opus-5`)
 - **Sandbox** (optional) → `-s <mode>` where mode is one of `read-only`, `workspace-write`, or `danger-full-access`
@@ -391,9 +391,9 @@ 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.
-- **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 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 pane 0 to that tmux session (`attachRequest` on `LaneConsolePane`) — it starts nothing and resumes nothing. Ctrl/Cmd+click adds `&pane=1`: the session view attaches pane 1 instead, widening a one-pane layout to two once for that request. Any other session opens its read-only transcript at `/sessions/<id>`; resuming it is a separate, explicit action there, because a resume re-reads the whole transcript into context.
+- **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 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 pane 0 to that tmux session (`attachRequest` on `LaneConsolePane`) — it starts nothing and resumes nothing. Ctrl/Cmd+click adds `&pane=1`: the session view attaches pane 1 instead, widening a one-pane layout to two once for that request. 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: Start/Stop (slot 0), Rename, the Model (AI Router) select, Create/update readme file (Claude only), 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").
-- **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 with the tool's model picker (and Claude's permission mode) whose **Start** opens a NEW session in the first pane slot with no live run (0–3, `POST /api/lanes/:id/start {slot}`; all four busy is refused) and then shows it, and **Recents** — the workspace's own sessions (`?lane=<id>`) with their cost and time, a live one opening its pane and any other its read-only transcript, 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.
+- **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 (a pane has no run form) — whose fields run in order **AI** (the session's own tool: every installed, enabled one, the workspace's by default), **AI Router** (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), and whose **Start** opens a NEW session in the first pane slot with no live run (0–3, `POST /api/lanes/:id/start {slot}`; all four busy is refused) and then shows it, 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 home's prompt box has a **Worktree** checkbox (Claude workspaces in a git repo), 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 today's console, split panes and the Files / Changes panel, with pane 0 attached to that run; the header's back arrow returns to the home. A browser notification for a workspace with a live pane opens it here directly.
 - **Untracked worktrees** are no longer listed in the sidebar; Settings → Git → **Worktrees** (`showUntracked`, hidden sources `claude` = `<repo>/.claude/worktrees/*` and `agenthub` = `LANES_ROOT`) now decides which of them the home's Add folder suggests.
@@ -402,18 +402,14 @@ The dashboard web UI merges workspaces and runs into a single **Workspace** page
 - **Renaming a workspace** — double-click its sidebar row (or Rename in the row menu) to edit in place. **Enter** saves via `PATCH /api/lanes/:id` with `{title}`, **Escape** and clicking away both cancel, and saving an empty name clears the title, which puts the folder name back in its place. Renaming is display-only — a managed workspace's branch name was slugified from its title once, at creation.
 - **Workspace-detail header row** — one row, and every per-workspace control lives on it: liveness + status, the workspace's name (read-only here — renaming is on the sidebar row; no "Workspace 23 ·" prefix — the id is on the row), time-on-stage, the pipeline picker, the Model (AI Router) select, the feature picker (time-on-stage and both pickers only while a pipeline template is installed; there are no stage chips here — the declared stage and the `auto: <stage>` detection both render in the PipelineMap directly below, so the chips were a second, smaller copy of the same two facts), and on the right the **Tools** menu (mcp sync / sync-base check / create-update readme, hidden when the workspace declares no runtime profile) and the split-view toggle. The detail block under it (the workspace card, the PipelineMap, the proof gallery) is always shown — there is no info toggle any more — and Delete lives in the sidebar row menu. Tools sits here rather than in Settings because every one of its actions runs against one workspace's `cwd` — in Settings it would need a workspace picker just to say which. **Create/update readme file** (Claude workspaces only — Codex has no slash commands) starts the workspace's terminal run with `/sg-all:sg-md-writing` as its first message, so the workspace opens already writing/refreshing its `CLAUDE.md`/`AGENTS.md` set; it needs the `sg-all` plugin installed in Claude Code, and without it the session just reports an unknown command. It used to be a checkbox in the Add-workspace modal: creating a workspace and writing its docs are separate decisions, and the second is worth re-running long after the first.
 - **Detail panel** — the selected workspace's declared stage, its inferred stage when detection leads, a full-width pipeline map, and a legend naming all five node states plus the dashed-amber inferred treatment Hidden while no pipeline template is installed (see "Pipeline stages and the five node states").
-- **Terminal** — a real interactive terminal (xterm.js) displaying the tmux session's PTY output, with full support for interactive commands, editors, and pagers. A live run keeps its rendered history and scroll position when scrolling. It grabs the keyboard the moment it appears, so typing goes into the pane without clicking it first, and when the pane's process ends — a double Ctrl+C out of `claude`, `exit`, a crash — the console returns to the run setup form on its own, with no "New run" click.
+- **Terminal** — a real interactive terminal (xterm.js) displaying the tmux session's PTY output, with full support for interactive commands, editors, and pagers. A live run keeps its rendered history and scroll position when scrolling. It grabs the keyboard the moment it appears, so typing goes into the pane without clicking it first. A pane has **no run form of its own**: a new session starts only from the workspace home's prompt box. **New run** under the terminal goes back to the home, and so does a single pane whose process ends (a double Ctrl+C out of `claude`, `exit`, a crash); a split pane with nothing to show offers **New session**, which opens the home too.
 - **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.
-- **Split view** — a layout toggle (one pane / two side by side / a 2×2 grid, drawn as icons rather than the words, with the count kept as each button's `aria-label` and tooltip) renders that many terminal panes side by side (`grid-cols-2` for 2, a 2×2 grid for 4). EVERY pane is bound to the sidebar's selection — there is no per-pane workspace picker — and each pane owns its own tmux session on that workspace: pane 0 is the workspace's `agenthub-lane-<id>` (its `run_id`), panes 1–3 are `agenthub-lane-<id>-<slot>` (`POST /api/lanes/:id/start` with `slot`). In split view each pane carries a one-line header — tool icon, workspace name, `slot N`, the run's model — and panes 1–3 a close button that kills only that pane's own session (`DELETE /api/run/agenthub-lane-<id>-<slot>`); slot 0 has none. A pane's **Active runs** leaves out the runs the other panes are showing, so one terminal is never attached twice side by side. Only the layout persists to `localStorage` (`agenthub.workspace.splitView`); a stored per-pane workspace id from an older build is ignored.
+- **Split view** — a layout toggle (one pane / two side by side / a 2×2 grid, drawn as icons rather than the words, with the count kept as each button's `aria-label` and tooltip) renders that many terminal panes side by side (`grid-cols-2` for 2, a 2×2 grid for 4). EVERY pane is bound to the sidebar's selection — there is no per-pane workspace picker — and each pane owns its own tmux session on that workspace: pane 0 is the workspace's `agenthub-lane-<id>` (its `run_id`), panes 1–3 are `agenthub-lane-<id>-<slot>` (`POST /api/lanes/:id/start` with `slot`). In split view each pane carries a one-line header — the icon of the AI tool its run is on, workspace name, `slot N`, the run's model — and panes 1–3 a close button that kills only that pane's own session (`DELETE /api/run/agenthub-lane-<id>-<slot>`); slot 0 has none. A pane's **Active runs** leaves out the runs the other panes are showing, so one terminal is never attached twice side by side. Only the layout persists to `localStorage` (`agenthub.workspace.splitView`); a stored per-pane workspace id from an older build is ignored.
 - **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>`.
 
-**A console pane follows the workspace it shows.** Selecting another workspace on the workspace list swaps every pane's cwd, run history and terminal over to the new workspace. If the new workspace already has a live session for that pane's slot in `GET /api/run`, the pane re-attaches to it immediately, so each pane sticks to its own `agenthub-lane-<id>[-<slot>]` tmux session; if it has none, the pane shows that workspace's setup form. Nothing of the previous workspace (a half-typed prompt, its terminal) carries over.
-
-The **working directory** field tracks the selected workspace's own `cwd` specifically, and re-syncs as soon as that path is known rather than only when the selection changes — a pane can render before `GET /api/lanes` has answered (the workspace list loads after the page mounts), and its workspace id never changes afterwards. `RunSetup` submits that string verbatim to `POST /api/lanes/:id/start`, so a cwd left over from the previous workspace or from the home default would start the run in the wrong folder. The home suggestion is used only while no workspace is selected at all.
-
-**Picking a session to resume starts it right away.** In the setup form's Fresh/Resume switch, choosing a session from the resume picker fires the start immediately — `POST /api/lanes/:id/start` with that `resumeSessionId` and the session's own `cwd` — and the pane switches straight to the terminal. A resume carries its own transcript, so there is nothing to type first: the prompt box stays optional for resumes (the Run button no longer requires it) and required for fresh runs. A resume also **sends no prompt at all** — whatever is left in that box is dropped rather than fired as an extra turn into the session being continued. Type into the tmux terminal once it's attached.
+**A console pane follows the workspace it shows.** Selecting another workspace on the workspace list swaps every pane's cwd, run history and terminal over to the new workspace. If the new workspace already has a live session for that pane's slot in `GET /api/run`, the pane re-attaches to it immediately, so each pane sticks to its own `agenthub-lane-<id>[-<slot>]` tmux session; if it has none, the pane is empty. Nothing of the previous workspace (a half-typed prompt, its terminal) carries over.
 
 ### Active runs list