Claude Fleet Monitor

Fleet monitoring for Claude Code and Codex sessions, with optional Pi lifecycle integration. See all your running agent sessions at a glance, get notified when one needs input, and jump to the right terminal tab instantly.

Features

• TUI Dashboard -- Textual-based interactive UI with search/filter, status-colored rows, and click-to-focus
• tongs Plugin -- embeds as a screen in tongs via the TongsPlugin ABC
• Process Discovery -- finds running Claude Code and Codex sessions cross-platform even before hooks fire
• MCP Server -- Claude Code and Codex sessions can query fleet status programmatically
• Terminal Focus -- switch to a session's tab and raise the window, across supported terminal backends
• Desktop Notifications -- notify-send alerts when a session has been idle for over 2 minutes
• Hooks Integration -- Claude Code and Codex hooks emit real-time status (running, idle, waiting, error) per session
• Per-Session Terminal Detection -- each session captures its terminal type at hook time, not at focus time

Harness support

The support matrix separates lifecycle ingestion from process identity and focus. A lifecycle event does not by itself prove that a process is discoverable, that a terminal target can be selected, or that a desktop window can be activated. See the adapter author guide and the implemented event, identity and focus contract before adding another harness.

The evidence behind this table has defined limits:

• The strict shell validation runs the existing hook through nine real shells in rootless Podman. Its 18 lifecycle cases, nine manual quoted-path controls and 108 generated-command checks use synthetic payloads. They do not prove live Claude or Codex processes, TTY discovery, terminal focus or GUI activation.
• The Pi validation runs a real Pi 0.85.0 process with Node.js 22.23.1 and Python 3.12.14 against a synthetic localhost provider. It validates lifecycle behavior and exact tmux pane selection in an isolated server. It does not claim a desktop window result.
• Platform-specific process and terminal behavior in the regular test suite is mocked. No live Claude or Codex runtime or desktop GUI acceptance is included in this matrix.

Supported Terminals

The table lists implemented backend capabilities and the strongest evidence behind each claim. Runtime availability, selected-target proof and window activation vary by environment and are reported as structured focus outcomes; a successful command alone is never reported as focus. Evidence labels: live (real program observed on Fedora 44 KDE Plasma Wayland), instrumented (real program with Fleet calls recorded), mocked (pytest with substituted OS calls), inspected (source or documentation only) and unverified (not observed).

"Yes" means the operation is attempted and reported as succeeded only after independent readback. Version support is the one version validated on the host, except zellij: the isolated validator passes on 0.44.2 through 0.45.1. zellij 0.44.1, the first release with focus-pane-id, selects panes but did not pass the two-client check; 0.44.0 and older have no focus-pane-id, so selection reports a failure instead of a guess.

On macOS, captured identifiers are validated (ITERM_SESSION_ID must be w<N>t<N>p<N>:<UUID>) and reach osascript only as arguments to the script's run handler, never as AppleScript source. Both adapters match the agent's controlling tty, read with ps at focus time; an agent without one has no target. When a session ID was captured, iTerm2 also requires it to match, so an ITERM_SESSION_ID inherited by a program launched from an iTerm2 shell cannot select the wrong session; without one (nested tmux parent routing) the tty alone must identify exactly one session. Terminal.app's AppleScript exposes no session ID, so its tab is matched by tty alone. Readback is part of the design, but neither adapter has been run on a Mac yet; see #55.

Nested terminals (e.g. tmux inside Konsole) are handled automatically: the focus command selects the exact pane, then routes window activation to the terminal emulator hosting a client that is attached to that pane. The structured result reports selection and activation separately, so a detached session or an unsupported parent gives an honest partial result. Kitty and Terminator stop the parent walk and report activation unsupported rather than climbing to whatever launched them (a multiplexer client carries no kitty socket or KITTY_PID, so kitty cannot raise its window as a parent). A zellij server is daemonized, so its ancestry never reaches a GUI. On Linux, Fleet instead finds the server in the agent's ancestry, maps its accepted sockets to client PIDs (a sock_diag netlink dump plus /proc/<pid>/fd links of your own zellij processes) and routes activation to the emulator hosting the one attached client. Only a plain zellij client or zellij attach counts as interactive and transient zellij action calls are ignored. Any other connected zellij process (web, watch, pipe, subscribe, run, edit, plugin or an unrecognized command line) is refused, because it may show the session somewhere else. It also refuses when several clients are attached, when the client processes do not match list-clients, when the session was renamed, or when the client exited meanwhile.

tmux selection uses stable session, window and pane IDs with selection readback. Parent-window routing considers only clients attached to the target session; detached sessions can still select their pane without activating a GUI window. When several attached clients show the target pane in different emulator windows, each client's parent is tried in turn. Routing stops after the first parent that sent a raise request (a KWin activation script that ran, an xdotool windowactivate, or a call to a parent's raise), even when the window or tab could not be confirmed afterwards. Focus then reports why, for example parent terminal konsole may have raised its window but could not confirm it (...), instead of trying another window. A parent that fails before sending any request (no unique GNOME or Ghostty X11 window, Konsole D-Bus owner unreadable, qdbus missing) lets the next client be tried. For Konsole, window matching happens inside the KWin script, so a script that ran but matched no unique window also stops routing. One rare case can still raise two windows: a KWin script run call that fails or times out is treated as no request, although KWin may have run it. See the isolated tmux validation for the tested routing behavior and its GUI evidence limits.

Terminator is detection only (#47, reported by @EmilienM). Sessions are labelled terminator and capture TERMINATOR_UUID, TERMINATOR_DBUS_NAME and TERMINATOR_DBUS_PATH, but focus reports an honest unsupported failure: Terminator's D-Bus interface cannot select a terminal or raise a window.

Kitty remote control

Kitty selection needs remote control, which Fleet never enables for you and never writes into kitty.conf. Add both settings yourself and restart kitty:

allow_remote_control socket-only
listen_on unix:${XDG_RUNTIME_DIR}/kitty-{kitty_pid}

Kitty then exports KITTY_LISTEN_ON, which the hook captures with KITTY_WINDOW_ID. Only unix: socket addresses (an absolute path or an @abstract name) are used; tcp:, fd: and relative addresses are dropped at capture. Without remote control or a unix: listen_on socket, focus reports "kitty remote control unavailable: needs allow_remote_control and a unix: listen_on socket" and changes nothing.

Selection also needs KITTY_PID, which the hook captures since this release: the kitty process it names must be an ancestor of the agent process and of the target window's child process that kitten @ ls reports. This keeps kitty variables leaked into another terminal, or a nested kitty that inherited an outer KITTY_LISTEN_ON, from selecting a same-numbered window in the wrong kitty. Sessions recorded earlier have no KITTY_PID and report "restart the agent session to enable kitty focus" without selecting.

Upgrade note: kitty sessions recorded before this release lose selection until the agent session is restarted, and kitty versions that do not export KITTY_PID lose selection.

Security warning: with allow_remote_control enabled, any local process that can reach the socket can control kitty, including sending text to its windows and running commands. Prefer socket-only over yes, keep the socket in a directory only you can access (as $XDG_RUNTIME_DIR above), avoid abstract @ sockets on shared hosts, and turn remote control off when you do not need it. Fleet only runs ls and focus-window and never sends a remote control password; if kitty requires one, focus reports the refusal instead of selecting.

Kitty window raise works on KDE Plasma only and needs, besides the selection requirements above:

• Exactly one OS window in that kitty process. KWin sees every OS window of a kitty process (including --single-instance windows) under one pid and cannot tell them apart, so focus then selects the tab but reports activation unavailable.
• qdbus and KWin on the session bus. KWin activates the single normal window owned by KITTY_PID; success needs the script to confirm KWin accepted that window as active and kitty to report the OS window focused within one second and still focused 0.2 s later.

Terminal detection limits

Terminal markers leak into child processes: Kitty started from a Konsole shell inherits KONSOLE_*, anything started from a Terminator shell inherits TERMINATOR_UUID, and a terminal launched from a tmux pane inherits TMUX. On Linux the hook therefore first walks its own process ancestry, reading only the process name and parent PID from /proc/<pid>/stat (never the environment or command line of another process, at most 64 steps). The nearest Konsole, Ghostty, GNOME Terminal, Terminator, Kitty, tmux, zellij or GNU screen ancestor sets the label, and that adapter records whichever of its markers are present. So Kitty started from Konsole is labelled kitty, GNU screen or zellij inside tmux or Konsole is labelled screen or zellij, and a Konsole window opened from a tmux pane is labelled konsole. A known emulator without a Fleet adapter also stops the walk and labels the session generic, which never selects or activates: Alacritty, foot, xterm, rxvt-unicode, WezTerm, xfce4-terminal, MATE Terminal, LXTerminal, QTerminal, Tilix, Ptyxis, GNOME Console (kgx), Terminology, Sakura, Tilda, Guake, cool-retro-term, Contour and the VS Code, VSCodium and Cursor terminals. So Alacritty launched from a tmux pane, foot launched from Kitty or WezTerm launched from Ghostty is labelled generic instead of targeting the launching terminal through its leaked markers. Yakuake, Kate and Dolphin embed Konsole, so they are not on that list. When the walk finds no known terminal or cannot read /proc, detection falls back to the fixed environment-variable order. Remaining limits:

• On macOS and Windows detection uses environment variables only, so the leaked-marker cases above keep the label of the launching terminal.
• A terminal adapter selected by ancestry can lack its own markers (for example Kitty without remote control), so focus reports its usual unavailable or unsupported failure rather than using the leaked markers.
• The same list stops the tmux and zellij parent walk: a multiplexer client inside one of these emulators reports that its parent terminal emulator has no Fleet adapter instead of raising the emulator that launched it. On macOS and Windows only the parent walk uses the list, and only names that match there (for example Alacritty and WezTerm; the VS Code family runs under different process names on macOS).
• An emulator missing from both lists is passed over, so the walk and the leaked markers can still reach the terminal that launched it.
• Records captured before an upgrade keep their old label and environment; start a fresh agent session to pick up new capture keys such as ZELLIJ_PANE_ID.

Install

pip install claude-fleet-monitor
claude-fleet install

Or install from source:

git clone https://github.com/andre-motta/claude-fleet-monitor.git
cd claude-fleet-monitor
pip install .
claude-fleet install

The installer updates Claude Code's ~/.claude/settings.json, writes Codex hooks to ~/.codex/hooks.json, and registers the Fleet MCP server for Claude Code and, when the Codex CLI is available, Codex. Restart your sessions after the first install. Codex requires you to review and trust the installed hooks through /hooks before they run.

Pi support is optional and requires Pi 0.84.4 or newer:

claude-fleet install --agent pi

This installs the dependency-free Pi lifecycle extension packaged with Fleet. It preserves other Pi extensions and does not register an MCP server. See the Pi integration guide for lifecycle, privacy, upgrade and removal behavior. --agent all installs Claude Code, Codex and Pi together.

tongs Integration

To use the fleet monitor as a plugin inside tongs:

pip install claude-fleet-monitor[tongs]

Then launch tongs and open the command palette (Ctrl+P) to find "Fleet Monitor".

Upgrading

pip install --upgrade claude-fleet-monitor

Claude Code and Codex hooks point to pip-installed entry points, so their upgrades take effect immediately. If Fleet moves to another virtual environment, run claude-fleet install --agent pi again to update Pi's exact extension and hook paths.

Dependencies

• python3 >= 3.10
• textual >= 1.0

Optional (for terminal focus):

• qdbus, qdbus6 or qdbus-qt6 -- Konsole tab switching and KWin activation for Konsole and Kitty (KDE)
• xdotool -- GNOME Terminal / X11 window focus
• kitten or kitty with remote control enabled -- Kitty window selection
• zellij and screen CLIs -- pane and window selection for those multiplexers
• notify-send -- desktop notifications (Linux)

Optional agent integration:

• Pi >= 0.84.4 and Node.js, installed separately

Usage

TUI Dashboard

claude-fleet monitor              # default 2s refresh
claude-fleet monitor --refresh 5  # 5s refresh

Navigate with arrow keys or mouse. Press Enter or click a row to focus that session's terminal. Press / to search/filter by repo name, detail, or status. Press q to quit.

Focus a Session

claude-fleet focus autofix         # by repo name
claude-fleet focus 2467709         # by PID
claude-fleet focus abc123          # by session ID prefix

The focus command reads the session's stored terminal type and uses the right API. It reports complete, partial or unavailable outcomes, with capability and evidence varying by terminal backend.

Quick Status (no TUI)

claude-fleet status

MCP Tools

Any Claude Code or Codex session with the fleet MCP server can use these tools:

Ask your agent: "what sessions are running?" or "focus on the autofix session".

How It Works

                                                              <-- MCP server
Claude Code sessions --\                                      <-- TUI monitor
  (hooks per event)     |                                      <-- tongs plugin
                       |-- write --> ~/.claude/fleet/*.json    <-- CLI status
Codex sessions --------|                                      <-- focus command
  (hooks per event)     |
Pi sessions ------------|
  (optional extension)  |
                       /
  (process discovery) -

1. Hooks fire on Claude Code and Codex events; the optional Pi extension translates Pi lifecycle events
2. Each hook captures the session's terminal type and PID, writes to ~/.claude/fleet/
3. Process discovery scans for claude and codex processes cross-platform to find sessions without hooks
4. Consumers (TUI, MCP, tongs plugin, CLI, focus) read the JSON files
5. Focus reads the session's terminal field and dispatches to the right terminal API

Terminal Detection Flow

Hook fires inside session
  --> Linux: nearest known terminal or multiplexer ancestor (/proc/<pid>/stat only)
  --> otherwise detect terminal via env vars (TMUX, KONSOLE_VERSION, ITERM_SESSION_ID, ...)
  --> capture terminal-specific env (socket paths, DBus service, session IDs)
  --> store in fleet JSON: {"terminal": "tmux", "terminal_env": {"TMUX": "..."}}

Focus command reads session JSON
  --> get_terminal_api("tmux") --> TmuxAPI
  --> find_tab(pid) --> switch_tab() --> raise_window()
  --> for nested terminals: detect parent terminal, chain to parent API

Session States

Architecture

src/claude_fleet_monitor/
    models.py           # SessionStatus enum, FleetSession dataclass
    hook.py             # Claude Code and Codex hook handler
    discovery.py        # Process discovery, session file I/O
    tui.py              # Textual standalone app (FleetMonitorApp)
    cli.py              # claude-fleet CLI entry point
    pi_install.py       # Optional Pi package lifecycle
    pi_extension/       # Dependency-free packaged Pi bridge
    focus.py            # Session lookup + terminal focus dispatch
    mcp_server.py       # FastMCP server
    tongs_plugin.py     # TongsPlugin ABC implementation
    widgets/
        session_table.py  # SessionTable(DataTable) widget
    views/
        fleet_screen.py   # FleetScreen(Screen) for tongs
    terminal_apis/
        base.py           # TerminalAPI ABC
        konsole.py        # KDE Konsole
        tmux.py           # tmux
        zellij.py         # zellij
        _unix_peers.py    # Linux unix-socket peer lookup (zellij clients)
        ghostty.py        # Ghostty (Linux, owner-window KWin/X11)
        gnome.py          # GNOME Terminal
        terminator.py     # Terminator (detection only)
        iterm2.py         # iTerm2
        macos_terminal.py # macOS Terminal.app
        windows_terminal.py # Windows Terminal (detection only)
        kitty.py          # Kitty (opt-in remote control)
        screen.py         # GNU screen
        generic.py        # Fallback (no target)
        parent.py         # Nested parent-terminal routing
        _env.py           # Env-only capture helpers
        _ancestry.py      # Linux hook-time ancestry walk (comm and ppid only)
        _applescript.py   # macOS osascript runner (argv-only data) and tty lookup

Known Limitations

• Same-title tabs in different windows (Konsole/KDE): Konsole window activation must match exactly one window of the owning Konsole process. When two windows show the same caption, focus selects the tab but reports activation as failed ("no unique Konsole window matched the tab title") instead of raising a guess.
• Wayland window activation: On Wayland/KDE, window raising uses KWin scripting via DBus. Other Wayland compositors may not support programmatic window activation.
• GNOME Terminal: No tab switching API available; window raise only for the exact owning window on X11. A server with several windows, including minimized ones or ones on other desktops, reports activation unavailable.
• Ghostty: Window activation requires a single managed Ghostty window (minimized and other-desktop windows count) and an X11 readback; with several windows, or on Wayland without xdotool readback, activation fails with a detail and no Alt+N keys are sent. This path is mocked only.
• Windows Terminal: Detection only. Its window titles follow the active tab and all windows usually share one process, so the session window cannot be identified without Win32 enumeration validated on Windows.
• Terminator: Detection only. Its D-Bus interface has no select or raise method, so focus reports an unsupported failure until Terminator gains one (#47).
• Kitty windows: Window raise is KDE Plasma (KWin) only, verified on Plasma Wayland (Plasma X11 and XWayland kitty are not verified), and needs a single OS window per kitty process; other desktops, several OS windows (including --single-instance), and sessions recorded before KITTY_PID was captured report activation unavailable with the reason.
• GNU screen windows: Selection is read back, but no GUI window activation is claimed. A screen session owns no window.
• zellij windows: Window activation is Linux only and needs exactly one attached interactive client; with several clients, or a zellij watch, zellij web or other non-interactive zellij process connected, Fleet cannot tell which window shows the pane and reports activation unavailable. Elsewhere zellij activation is unavailable. Real GUI activation through the client's emulator is not live-validated yet: the live validator routes to an instrumented parent only.
• GNU screen and zellij with several displays or clients: GNU screen switches only the most recently attached display, and zellij moves only the client that most recently received input; other displays and clients keep their own window or pane. Both need an attached display or client: a detached session reports a failed selection.
• zellij socket directory: Every zellij call targets the session's socket directory: on Linux it is derived from the zellij server's command line, otherwise the ZELLIJ_SOCKET_DIR captured at hook time is used, and without either zellij's default applies. A session that cannot be found reports which socket directory was searched.
• zellij selection proof: Selection succeeds only when a client that was elsewhere moves to the pane, or when every attached client already showed it ("pane already focused"). An idle client that already showed the pane while the active client did not move is a failure.
• Generic fallback: Unknown terminals get no selection or window raise; the earlier best-effort raise could activate an unrelated window and was removed.

Configuration

Environment Variables

Uninstall

claude-fleet uninstall              # removes hooks, MCP config, and data
claude-fleet uninstall --keep-data  # keeps ~/.claude/fleet/
claude-fleet uninstall --agent pi   # removes only Fleet's owned Pi extension

Contributing

See CONTRIBUTING.md for development setup, code style, and PR process. Harness contributors should follow the adapter author guide and the implemented harness contract. Agent-led initiatives follow the SDLC profile. Future desktop UI work is tracked in harnesses and desktop. Focusing ChatGPT desktop conversations is not supported (evidence).

License

MIT