claude-code-gnome-extension/hooks/claude-status-hook.py

#!/usr/bin/env python3
"""Claude Code hook -> per-session state file for the GNOME panel indicator.

Reads one hook event as JSON on stdin and maps it to a session state, written
to $XDG_STATE_HOME/claude-code-status/<session_id>.json. The GNOME extension
watches that directory; no polling, no daemon, no socket.

Design notes that are easy to get wrong:

* Writes are skipped when the state does not change. PostToolUse fires on every
  tool call, and its only job here is to clear "blocked" once a permission has
  been granted -- letting it rewrite the file each time would make the directory
  monitor fire hundreds of times per turn for no new information.

* Hooks are registered async, so two events can race (the last PostToolUse of a
  turn against that turn's Stop). The whole read-decide-write runs under a file
  lock and an event older than the stored one is refused; without both, a late
  "busy" buries "waiting" and the panel claims a session is working while it
  actually waits for input.

* No stdlib import beyond what is needed: this runs once per tool call.
"""

import fcntl
import json
import os
import sys
import time

STATE_DIR = os.path.join(
    os.environ.get("XDG_STATE_HOME") or os.path.expanduser("~/.local/state"),
    "claude-code-status",
)

# Notification covers several unrelated things; only some mean "the session
# stopped and is asking me something". auth_success / elicitation_complete /
# elicitation_response are progress chatter and must not touch the state.
# Observed: a question put to the user (AskUserQuestion) arrives as
# "permission_prompt" too, with the same generic message as a tool asking to
# run. The two are therefore not separable here, which is why the panel has one
# "blocked" state rather than telling a permission from a question.
NOTIFICATION_STATES = {
    "permission_prompt": "blocked",
    "agent_needs_input": "blocked",
    "elicitation_dialog": "blocked",
    "idle_prompt": "waiting",
    "agent_completed": "waiting",
}

EVENT_STATES = {
    # A session that has just opened is waiting for your first prompt, which is
    # the same thing as one that has finished a turn: the input line is free
    # and the next move is yours. It had a state of its own once; it was only
    # ever reachable before the first prompt, so it bought a fourth glyph in
    # the panel that nobody saw.
    "SessionStart": "waiting",
    "UserPromptSubmit": "busy",
    "PreCompact": "busy",
    "PostToolUse": "busy",
    "Stop": "waiting",
}


def debug_log(event):
    """Append raw events when a 'debug' marker file exists in the state dir.

    Gated on a file rather than an env var because the hook inherits claude's
    environment, which cannot be changed without restarting the session.
    """
    marker = os.path.join(STATE_DIR, "debug")
    if not os.path.exists(marker):
        return
    try:
        with open(marker, "a") as fh:
            stamped = dict(event, _at=time.strftime("%H:%M:%S"))
            fh.write(json.dumps(stamped, sort_keys=True)[:2000] + "\n")
    except OSError:
        pass


def derive_state(event):
    """Return the new state, 'end' to drop the session, or None to ignore."""
    name = event.get("hook_event_name")
    if name == "SessionEnd":
        return "end"
    # A notification is honoured whoever raised it: it means a human is needed,
    # and that is just as true when the agent that got stuck is a subagent.
    if name == "Notification":
        return NOTIFICATION_STATES.get(event.get("notification_type"))
    # Everything else describes work, and work done by a subagent is not the
    # main agent's state. Measured: a subagent's tool call does reach the
    # parent session's hooks, as PostToolUse carrying agent_id and agent_type.
    #
    # This matters most for background subagents. There the main agent ends its
    # turn first -- Stop, so "waiting" -- and the subagents keep going, so their
    # PostToolUse arrives afterwards and would flip the session back to "busy".
    # The panel would then read "working" for a session whose input line is free
    # and which is waiting for you, which is the exact confusion it exists to
    # prevent. Synchronous subagents need no special handling either way: the
    # main agent is mid-turn, so its own earlier events already say "busy".
    if event.get("agent_id"):
        return None
    return EVENT_STATES.get(name)


def read_environ(pid):
    """Environment of a process as a dict, empty if it is gone or not ours."""
    try:
        with open("/proc/%d/environ" % pid, "rb") as fh:
            raw = fh.read()
    except OSError:
        return {}
    env = {}
    for entry in raw.split(b"\0"):
        if not entry:
            continue
        key, sep, value = entry.partition(b"=")
        if sep:
            env[key.decode("utf-8", "replace")] = value.decode("utf-8", "replace")
    return env


def read_cmdline(pid):
    try:
        with open("/proc/%d/cmdline" % pid, "rb") as fh:
            return fh.read().replace(b"\0", b" ").decode("utf-8", "replace")
    except OSError:
        return ""


def parent_of(pid):
    try:
        with open("/proc/%d/status" % pid, "r") as fh:
            for line in fh:
                if line.startswith("PPid:"):
                    return int(line.split()[1])
    except (OSError, ValueError):
        pass
    return 0


def find_claude_pid():
    """Nearest ancestor that is the claude process itself, or 0 if unknown.

    The hook is spawned through a shell, so the immediate parent is usually not
    claude. Walking beyond a handful of levels risks latching onto an outer
    claude when one session drives another, so the search stops early.

    Returning 0 rather than guessing matters: the reader deletes state files
    whose pid is gone, and the obvious fallback -- the shell that spawned this
    hook -- exits milliseconds later, which would make the session flicker in
    and out of the panel forever.
    """
    pid = os.getppid()
    for _ in range(6):
        if pid <= 1:
            break
        # Matched anywhere in the command line, not just argv[0]: installs that
        # run it as `node .../claude/cli.js` are just as valid as a direct one.
        if "claude" in read_cmdline(pid):
            return pid
        pid = parent_of(pid)
    return 0


def alive(pid):
    return pid > 0 and os.path.exists("/proc/%d" % pid)


def sweep_dead(keep):
    """Drop state files whose claude process is gone.

    A killed terminal never sends SessionEnd, so files leak. Cleaning up on
    SessionStart keeps the sweep off the hot path -- the extension only has to
    hide stale entries, not own their lifetime.
    """
    try:
        names = os.listdir(STATE_DIR)
    except OSError:
        return
    for name in names:
        if not name.endswith(".json") or name == keep:
            continue
        path = os.path.join(STATE_DIR, name)
        try:
            with open(path, "r") as fh:
                pid = json.load(fh).get("pid", 0)
        except (OSError, ValueError, AttributeError):
            continue
        # pid 0 means the hook could not identify the process; there is nothing
        # to test for liveness, so leave it to the reader's age cutoff.
        if pid and not alive(pid):
            for victim in (path, path + ".lock"):
                try:
                    os.unlink(victim)
                except OSError:
                    pass


def write_atomic(path, payload):
    tmp = "%s.%d.tmp" % (path, os.getpid())
    with open(tmp, "w") as fh:
        json.dump(payload, fh)
    os.replace(tmp, path)


def apply_event(event, state, path, now):
    """Read the current state, decide, and write. Must run under the lock."""
    if event.get("hook_event_name") == "SessionStart":
        # Swept before any early return: a resumed session keeps its id, so its
        # SessionStart finds an unchanged state and would otherwise bail out
        # before ever reaching the sweep.
        sweep_dead(keep=os.path.basename(path))

    if state == "end":
        for victim in (path, path + ".lock"):
            try:
                os.unlink(victim)
            except OSError:
                pass
        return

    previous = None
    try:
        with open(path, "r") as fh:
            previous = json.load(fh)
    except (OSError, ValueError):
        previous = None
    if not isinstance(previous, dict):
        previous = None

    # Normalised here so the comparison below is against what would actually be
    # stored: comparing a stored "" to a raw notification message rewrites the
    # file on every idle_prompt for no change at all.
    message = event.get("message", "") if state == "blocked" else ""

    if previous:
        # Auto-compaction raises SessionStart again, in the middle of a turn the
        # session is still working on. Taking it at face value would flip a busy
        # session to idle until the next tool call corrected it.
        if event.get("hook_event_name") == "SessionStart" and event.get("source") == "compact":
            return
        # Refuse events that lost a race with a newer one.
        if previous.get("event_ts", 0) > now:
            return
        # Nothing new to publish: stay quiet so the directory monitor stays quiet.
        if previous.get("state") == state and previous.get("message", "") == message:
            return

    claude_pid = find_claude_pid()
    env = read_environ(claude_pid) if claude_pid else {}

    write_atomic(path, {
        "session_id": event.get("session_id"),
        "state": state,
        "cwd": event.get("cwd") or "",
        # Age is measured from the moment the state was entered, not from the
        # last event, so "waiting 40 min" survives unrelated later writes.
        "since": previous["since"] if previous and previous.get("state") == state else now,
        "event_ts": now,
        # 0 means "could not tell"; the reader must not take that for "dead".
        "pid": claude_pid,
        "event": event.get("hook_event_name", ""),
        "notification_type": event.get("notification_type", ""),
        "message": message,
        "zellij_session": env.get("ZELLIJ_SESSION_NAME", ""),
        "zellij_pane": env.get("ZELLIJ_PANE_ID", ""),
        "transcript": event.get("transcript_path", ""),
    })


def main():
    now = time.time()
    try:
        event = json.load(sys.stdin)
    except (ValueError, OSError):
        return 0
    if not isinstance(event, dict):
        return 0

    session_id = event.get("session_id")
    if not session_id or "/" in session_id:
        return 0

    debug_log(event)

    state = derive_state(event)
    if state is None:
        return 0

    os.makedirs(STATE_DIR, exist_ok=True)
    path = os.path.join(STATE_DIR, "%s.json" % session_id)

    # Hooks for one session run concurrently -- the last PostToolUse of a turn
    # races that turn's Stop. Comparing timestamps is not enough on its own:
    # without a lock both processes read the same "previous" and the loser's
    # write still lands last, pinning a finished session at "busy". The lock is
    # a separate file because write_atomic replaces the inode of the real one.
    with open(path + ".lock", "w") as lock:
        fcntl.flock(lock, fcntl.LOCK_EX)
        apply_event(event, state, path, now)
    return 0


if __name__ == "__main__":
    try:
        sys.exit(main())
    except Exception:
        # A hook that fails loudly would spam every session with error output;
        # a missing panel update is the cheaper failure.
        sys.exit(0)