#!/usr/bin/env python3
"""Failsafe halt for cross-agent comms.

See cross-agent-halt.md. Touches ~/.config/cross-agent-comms/HALT and stops
the cross-agent-watch systemd user service. With --tailnet, propagates the
HALT file to every peer in peers.toml via SSH; reports per-peer status with
non-zero exit on partial halt.

Does NOT pkill in-flight scripts — they detect HALT on next iteration and
stop themselves.
"""

from __future__ import annotations

import argparse
import subprocess
import sys
import tomllib
from pathlib import Path

CONFIG_DIR = Path.home() / ".config" / "cross-agent-comms"
HALT_FILE = CONFIG_DIR / "HALT"
PEERS_TOML = CONFIG_DIR / "peers.toml"

EXIT_OK = 0
EXIT_PARTIAL = 1


def err(msg: str) -> None:
    print(msg, file=sys.stderr)


def write_halt_file(reason: str) -> None:
    CONFIG_DIR.mkdir(parents=True, exist_ok=True)
    HALT_FILE.write_text((reason + "\n") if reason else "")


def stop_watcher_service() -> None:
    """Best-effort stop of the systemd watcher service. Failures are logged but not fatal."""
    try:
        subprocess.run(
            ["systemctl", "--user", "stop", "cross-agent-watch.path"],
            capture_output=True, text=True, timeout=5,
        )
    except (FileNotFoundError, subprocess.TimeoutExpired):
        # Watcher service may not be installed — fine.
        pass


def load_peers() -> dict:
    if not PEERS_TOML.exists():
        return {}
    try:
        return tomllib.loads(PEERS_TOML.read_text())
    except (tomllib.TOMLDecodeError, OSError) as e:
        err(f"cannot parse peers.toml: {e}")
        return {}


def ssh_touch_halt(host: str, ssh_user: str | None, reason: str) -> tuple[bool, str]:
    target = f"{ssh_user}@{host}" if ssh_user else host
    # Build the remote command. Quote the reason carefully.
    remote_cmd = (
        f"mkdir -p ~/.config/cross-agent-comms && "
        f"printf %s {_sh_quote(reason)} > ~/.config/cross-agent-comms/HALT"
    )
    try:
        result = subprocess.run(
            ["ssh", "-o", "ConnectTimeout=3", "-o", "BatchMode=yes", target, remote_cmd],
            capture_output=True, text=True, timeout=10,
        )
    except (FileNotFoundError, subprocess.TimeoutExpired):
        return False, "ssh unavailable or timed out"
    if result.returncode == 0:
        return True, "HALT file written"
    return False, (result.stderr.strip().splitlines() or [f"exit {result.returncode}"])[-1]


def _sh_quote(s: str) -> str:
    return "'" + s.replace("'", "'\"'\"'") + "'"


def main() -> int:
    parser = argparse.ArgumentParser(description="Halt all cross-agent comms on this machine (and optionally tailnet).")
    parser.add_argument("reason", nargs="?", default="", help="Optional human-readable reason")
    parser.add_argument("--tailnet", action="store_true",
                        help="Propagate HALT to every peer in peers.toml")
    args = parser.parse_args()

    # Local halt.
    write_halt_file(args.reason)
    stop_watcher_service()
    print("Halting locally       ✓ (HALT file written)")

    if not args.tailnet:
        print()
        print(f"Halt active. Remove {HALT_FILE} or run cross-agent-resume to clear.")
        print("Agent polling will stop within ~5 min (one cadence cycle).")
        return EXIT_OK

    peers = load_peers().get("peers", {})
    if not peers:
        print()
        print("No peers configured in peers.toml — local-only halt complete.")
        return EXIT_OK

    print()
    successes = 1  # local already counted
    failures = []
    for name, cfg in sorted(peers.items()):
        host = cfg.get("host", name)
        ssh_user = cfg.get("ssh_user")
        ok, detail = ssh_touch_halt(host, ssh_user, args.reason)
        marker = "✓" if ok else "✗"
        print(f"Halting {host:<28} {marker} ({detail})")
        if ok:
            successes += 1
        else:
            failures.append(f"{name} ({host}): {detail}")

    print()
    total = len(peers) + 1
    if failures:
        print(f"PARTIAL HALT: {successes}/{total} machines halted.")
        for f in failures:
            print(f"  - {f}")
        print("Resolve the failures or manually halt each machine.")
        return EXIT_PARTIAL
    print(f"Halt active across {total} machine(s).")
    return EXIT_OK


if __name__ == "__main__":
    sys.exit(main())