feat: workspace aliases, tab groups of split panes, native path picker (v2.1.0)

- /api/workspaces and `agenthub workspace(s)` / `--workspace` as aliases of
  /api/lanes and `agenthub lanes` / `--lane`; old names print one stderr note.
  REPL `help lanes|workspace|workspaces` resolves through the aliases.
- A workspace holds up to ten sessions (slots 0-9); every console tab is a
  group of 1-4 split panes (PaneGroups, agenthub.workspace.paneLayout);
  parseGroups keeps the stored active tab when an earlier one is dropped.
- Browse button beside path fields: POST /api/lanes/pick-path opens the OS
  picker on the server's desktop — loopback only and no forwarding header
  (EREMOTE), a display failure is ENODIALOG not a Cancel, the dialog is
  killed when the request closes, a folder field falls back to the in-app
  browser on any failure.
- Changes rail counts chip, image viewer (/git/raw), status bar session
  counts and per-day cost (`date=` on /api/pricing/cost).
- /agenthub-open and /agenthub-doctor run from the INSTALLED build
  (supersededBy), doctor offers fixes behind two confirmations; plugin-open
  treats a locked bootstrap as non-fatal.
- New-terminal shell waits for the first attach (issue #55).
- repo-onboarding / debug-live-issue skills removed.
- OpenAPI: pick-path, lane/date on /pricing/cost, tool on /run/history,
  /api/workspaces mount.

docs/PLUGINS.md

@@ -87,7 +87,7 @@ checkout unnecessary.
 | The `agenthub` CLI | a launcher written to `~/.local/bin/agenthub` |
 | The dashboard UI (`/run` and every other client route) | built into the runtime dir by the bootstrap, so it works the moment `claude` starts |
 | `/agenthub-doctor`, `/agenthub-update`, `/agenthub-open` | `plugins/agenthub/commands/` |
-| The skills (`repo-onboarding`, `debug-live-issue`, `update-project-docs`, `file-headers`) | `skills/` at the repo root — which IS the plugin root, so they are auto-discovered as plugin skills |
+| The skills (`update-project-docs`, `file-headers`) | `skills/` at the repo root — which IS the plugin root, so they are auto-discovered as plugin skills |
 
 Plugin skills are namespaced: they are invoked as `/agenthub:<name>`, with the bare
 `/<name>` working as an alias unless another skill or command claims that name.
@@ -172,8 +172,8 @@ So the bootstrap now asks first (`supersededBy`): if Claude Code's
 `~/.claude/plugins/installed_plugins.json` records a **sibling** directory as
 the installed build of this plugin, this build logs one line and returns
 `superseded` without touching dependencies, the unit, or the server. `--force`
-does not override it — the self-update chain runs `--force` from the NEW
-directory, which is never superseded, so the only `--force` this can refuse is
+does not override it — the self-update chain and `/agenthub-update` run
+`--force` from the NEW directory, which is never superseded, so the only `--force` this can refuse is
 one that would deliberately downgrade.
 
 It cannot hand over to the new build either: the process it would have to
@@ -338,9 +338,9 @@ courtesy of `Restart=always`.
 
 | Command | Does |
 |---|---|
-| `/agenthub-doctor` | Node version, bootstrap state, runtime deps, server liveness, duplicate hooks, CLI launcher + PATH, **systemd** (`WARN` when the unit names a retired plugin root — the dashboard will not survive a reboot — or when it is installed but stopped; no unit at all is fine), **tmux** (`WARN` when absent — only the run console, `agenthub lanes shell` and session reloads need it), UI bundle |
-| `/agenthub-update` | Pull the latest `agenthub` release via `claude plugin marketplace update` + `claude plugin update agenthub@<marketplace> -y`, then reinstall dependencies and restart the server (`plugin-bootstrap.js --force`). The plugin pull needs a manual `/reload-plugins` afterward to take effect in the current session — not scriptable from a command. |
-| `/agenthub-open` | Rebuild the UI bundle and print the dashboard URL. Re-runs the bootstrap first when the server is down or still executing a plugin root that a mid-session `/plugin` update retired, so a fresh bundle never talks to an older server's routes |
+| `/agenthub-doctor` | Node version, bootstrap state, runtime deps, server liveness, duplicate hooks, CLI launcher + PATH, **systemd** (`WARN` when the unit names a retired plugin root — the dashboard will not survive a reboot — or when it is installed but stopped; no unit at all is fine), **tmux** (`WARN` when absent — only the run console, `agenthub workspace shell` and session reloads need it), UI bundle. On any `FAIL`/`WARN` it asks whether to fix them, then lists the exact steps (one `plugin-bootstrap.js --force` from the installed build for deps/server/hooks/CLI launcher/stale unit, Node ≥ 22.5 through the user's version manager, the tmux package, the PATH line, …) and runs them only after a second yes; disk, a foreign unit, tmux built from source and an older running tmux server are reported, never touched. `plugin-doctor.js` itself stays read-only |
+| `/agenthub-update` | Pull the latest `agenthub` release via `claude plugin marketplace update` + `claude plugin update agenthub@<marketplace> -y`, then reinstall dependencies and restart the server with `plugin-bootstrap.js --force` run from the build that is INSTALLED now (`supersededBy()` of this session's root, else that root — the old root's bootstrap would refuse as `superseded`), and run the doctor. The dashboard is on the new version at once; only this session's own commands and skills wait for `/reload-plugins` or a new session. |
+| `/agenthub-open` | Rebuild the UI bundle and print the dashboard URL. Re-runs the bootstrap first when the server is down or still executing a plugin root that a mid-session `/plugin` update retired, so a fresh bundle never talks to an older server's routes. `plugin-open.js` exits 1 when the build fails or that bootstrap does not answer `ok`, and the command then runs the `/agenthub-doctor` flow and retries the build once after the approved fixes |
 
 ### Where things live