hermes-agent/tui_gateway/entry.py
Teknium dd789a4fdf
fix(mcp): move discovery out of model_tools import side effect (#16856) (#16899)
model_tools.py ran discover_mcp_tools() as a module-level side effect.
discover_mcp_tools() uses a blocking 120s wait internally (via
_run_on_mcp_loop -> future.result(timeout=120)).

The gateway lazy-imports run_agent -> model_tools on the first user
message, which happens inside the asyncio event loop thread.  A slow or
unreachable MCP server therefore froze Discord shard heartbeats and
Telegram polling for up to 120s on the first message after gateway
start.

Fix: remove the module-level call.  Every entry point now runs
discovery explicitly at its own startup, using the context-appropriate
blocking/non-blocking pattern:

- gateway/run.py:       loop.run_in_executor(None, discover_mcp_tools)
                        before platforms start accepting traffic
- hermes_cli/main.py:   inline (no event loop at CLI startup)
- tui_gateway/entry.py: inline (sync stdin loop, no event loop)
- acp_adapter/entry.py: inline before asyncio.run()

Closes #16856.
2026-04-28 01:17:58 -07:00

151 lines
5.6 KiB
Python

import json
import os
import signal
import sys
import time
import traceback
from tui_gateway import server
from tui_gateway.server import _CRASH_LOG, dispatch, resolve_skin, write_json
from tui_gateway.transport import TeeTransport
def _install_sidecar_publisher() -> None:
"""Mirror every dispatcher emit to the dashboard sidebar via WS.
Activated by `HERMES_TUI_SIDECAR_URL`, set by the dashboard's
``/api/pty`` endpoint when a chat tab passes a ``channel`` query param.
Best-effort: connect failure or runtime drop falls back to stdio-only.
"""
url = os.environ.get("HERMES_TUI_SIDECAR_URL")
if not url:
return
from tui_gateway.event_publisher import WsPublisherTransport
server._stdio_transport = TeeTransport(
server._stdio_transport, WsPublisherTransport(url)
)
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)
# SIGPIPE: ignore, don't exit. The old SIG_DFL killed the process
# silently whenever a *background* thread (TTS playback chain, voice
# debug stderr emitter, beep thread) wrote to a pipe the TUI had gone
# quiet on — even though the main thread was perfectly fine waiting on
# stdin. Ignoring the signal lets Python raise BrokenPipeError on the
# offending write (write_json already handles that with a clean
# sys.exit(0) + _log_exit), which keeps the gateway alive as long as
# the main command pipe is still readable. Terminal signals still
# route through _log_signal so kills and hangups are diagnosable.
signal.signal(signal.SIGPIPE, signal.SIG_IGN)
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():
_install_sidecar_publisher()
# MCP tool discovery — inline is safe here: TUI entry is a plain
# sync loop with no asyncio event loop to block. Previously ran as
# a model_tools.py module-level side effect; moved to explicit
# startup calls to avoid freezing the gateway's loop on lazy import
# (#16856).
try:
from tools.mcp_tool import discover_mcp_tools
discover_mcp_tools()
except Exception:
pass
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()