hermes-agent/tui_gateway/entry.py

import json
import os
import signal
import sys
import time
import traceback

from tui_gateway.server import _CRASH_LOG, dispatch, resolve_skin, write_json


def _log_signal(signum: int, frame) -> None:
    """Capture WHICH thread and WHERE a termination signal hit us.

    SIG_DFL for SIGPIPE kills the process silently the instant any
    background thread (TTS playback, beep, voice status emitter, etc.)
    writes to a stdout the TUI has stopped reading.  Without this
    handler the gateway-exited banner in the TUI has no trace — the
    crash log never sees a Python exception because the kernel reaps
    the process before the interpreter runs anything.
    """
    name = {
        signal.SIGPIPE: "SIGPIPE",
        signal.SIGTERM: "SIGTERM",
        signal.SIGHUP: "SIGHUP",
    }.get(signum, f"signal {signum}")
    try:
        os.makedirs(os.path.dirname(_CRASH_LOG), exist_ok=True)
        with open(_CRASH_LOG, "a", encoding="utf-8") as f:
            f.write(
                f"\n=== {name} received · {time.strftime('%Y-%m-%d %H:%M:%S')} ===\n"
            )
            if frame is not None:
                f.write("main-thread stack at signal delivery:\n")
                traceback.print_stack(frame, file=f)
            # All live threads — signal may have been triggered by a
            # background thread (write to broken stdout from TTS, etc.).
            import threading as _threading
            for tid, th in _threading._active.items():
                f.write(f"\n--- thread {th.name} (id={tid}) ---\n")
                f.write("".join(traceback.format_stack(sys._current_frames().get(tid))))
    except Exception:
        pass
    print(f"[gateway-signal] {name}", file=sys.stderr, flush=True)
    sys.exit(0)


signal.signal(signal.SIGPIPE, _log_signal)
signal.signal(signal.SIGTERM, _log_signal)
signal.signal(signal.SIGHUP, _log_signal)
signal.signal(signal.SIGINT, signal.SIG_IGN)


def _log_exit(reason: str) -> None:
    """Record why the gateway subprocess is shutting down.

    Three exit paths (startup write fail, parse-error-response write fail,
    dispatch-response write fail, stdin EOF) all collapse into a silent
    sys.exit(0) here.  Without this trail the TUI shows "gateway exited"
    with no actionable clue about WHICH broken pipe or WHICH message
    triggered it — the main reason voice-mode turns look like phantom
    crashes when the real story is "TUI read pipe closed on this event".
    """
    try:
        os.makedirs(os.path.dirname(_CRASH_LOG), exist_ok=True)
        with open(_CRASH_LOG, "a", encoding="utf-8") as f:
            f.write(
                f"\n=== gateway exit · {time.strftime('%Y-%m-%d %H:%M:%S')} "
                f"· reason={reason} ===\n"
            )
    except Exception:
        pass
    print(f"[gateway-exit] {reason}", file=sys.stderr, flush=True)


def main():
    if not write_json({
        "jsonrpc": "2.0",
        "method": "event",
        "params": {"type": "gateway.ready", "payload": {"skin": resolve_skin()}},
    }):
        _log_exit("startup write failed (broken stdout pipe before first event)")
        sys.exit(0)

    for raw in sys.stdin:
        line = raw.strip()
        if not line:
            continue

        try:
            req = json.loads(line)
        except json.JSONDecodeError:
            if not write_json({"jsonrpc": "2.0", "error": {"code": -32700, "message": "parse error"}, "id": None}):
                _log_exit("parse-error-response write failed (broken stdout pipe)")
                sys.exit(0)
            continue

        method = req.get("method") if isinstance(req, dict) else None
        resp = dispatch(req)
        if resp is not None:
            if not write_json(resp):
                _log_exit(f"response write failed for method={method!r} (broken stdout pipe)")
                sys.exit(0)

    _log_exit("stdin EOF (TUI closed the command pipe)")


if __name__ == "__main__":
    main()