5a2fcaab39
- detect Telegram getUpdates conflicts and stop polling cleanly instead of retry-spamming forever
- add a machine-local token-scoped lock so different HERMES_HOME profiles on the same host can't poll the same bot token at once
- persist gateway runtime health/fatal adapter state and surface it in ● hermes-gateway.service - Hermes Agent Gateway - Messaging Platform Integration
Loaded: loaded (/home/teknium/.config/systemd/user/hermes-gateway.service; enabled; preset: enabled)
Active: active (running) since Sat 2026-03-14 09:25:35 PDT; 2h 45min ago
Invocation: 8879379b25994201b98381f4bd80c2af
Main PID: 1147926 (python)
Tasks: 16 (limit: 76757)
Memory: 151.4M (peak: 168.1M)
CPU: 47.883s
CGroup: /user.slice/user-1000.slice/user@1000.service/app.slice/hermes-gateway.service
├─1147926 /home/teknium/.hermes/hermes-agent/venv/bin/python -m hermes_cli.main gateway run --replace
└─1147966 node /home/teknium/.hermes/hermes-agent/scripts/whatsapp-bridge/bridge.js --port 3000 --session /home/teknium/.hermes/whatsapp/session --mode self-chat
Mar 14 09:27:03 teknium-dev python[1147926]: 🔄 Retrying API call (2/3)...
Mar 14 09:27:04 teknium-dev python[1147926]: [409B blob data]
Mar 14 09:27:04 teknium-dev python[1147926]: Content: ''
Mar 14 09:27:04 teknium-dev python[1147926]: ❌ Max retries (3) for empty content exceeded.
Mar 14 09:27:07 teknium-dev python[1147926]: [1K blob data]
Mar 14 09:27:07 teknium-dev python[1147926]: Content: ''
Mar 14 09:27:07 teknium-dev python[1147926]: 🔄 Retrying API call (1/3)...
Mar 14 09:27:12 teknium-dev python[1147926]: [1.7K blob data]
Mar 14 09:27:12 teknium-dev python[1147926]: Content: ''
Mar 14 09:27:12 teknium-dev python[1147926]: 🔄 Retrying API call (2/3)...
⚠ Installed gateway service definition is outdated
Run: hermes gateway restart # auto-refreshes the unit
✓ Gateway service is running
✓ Systemd linger is enabled (service survives logout)
- cleanly exit non-retryable startup conflicts without triggering service restart loops
Tests:
- gateway status runtime-state helpers
- Telegram token-lock and polling-conflict behavior
- GatewayRunner clean exit on non-retryable startup conflict
- CLI runtime health summary
102 lines
4.0 KiB
Python
102 lines
4.0 KiB
Python
"""Tests for gateway runtime status tracking."""
|
|
|
|
import json
|
|
import os
|
|
|
|
from gateway import status
|
|
|
|
|
|
class TestGatewayPidState:
|
|
def test_write_pid_file_records_gateway_metadata(self, tmp_path, monkeypatch):
|
|
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
|
|
|
|
status.write_pid_file()
|
|
|
|
payload = json.loads((tmp_path / "gateway.pid").read_text())
|
|
assert payload["pid"] == os.getpid()
|
|
assert payload["kind"] == "hermes-gateway"
|
|
assert isinstance(payload["argv"], list)
|
|
assert payload["argv"]
|
|
|
|
def test_get_running_pid_rejects_live_non_gateway_pid(self, tmp_path, monkeypatch):
|
|
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
|
|
pid_path = tmp_path / "gateway.pid"
|
|
pid_path.write_text(str(os.getpid()))
|
|
|
|
assert status.get_running_pid() is None
|
|
assert not pid_path.exists()
|
|
|
|
|
|
class TestGatewayRuntimeStatus:
|
|
def test_write_runtime_status_records_platform_failure(self, tmp_path, monkeypatch):
|
|
monkeypatch.setenv("HERMES_HOME", str(tmp_path))
|
|
|
|
status.write_runtime_status(
|
|
gateway_state="startup_failed",
|
|
exit_reason="telegram conflict",
|
|
platform="telegram",
|
|
platform_state="fatal",
|
|
error_code="telegram_polling_conflict",
|
|
error_message="another poller is active",
|
|
)
|
|
|
|
payload = status.read_runtime_status()
|
|
assert payload["gateway_state"] == "startup_failed"
|
|
assert payload["exit_reason"] == "telegram conflict"
|
|
assert payload["platforms"]["telegram"]["state"] == "fatal"
|
|
assert payload["platforms"]["telegram"]["error_code"] == "telegram_polling_conflict"
|
|
assert payload["platforms"]["telegram"]["error_message"] == "another poller is active"
|
|
|
|
|
|
class TestScopedLocks:
|
|
def test_acquire_scoped_lock_rejects_live_other_process(self, tmp_path, monkeypatch):
|
|
monkeypatch.setenv("HERMES_GATEWAY_LOCK_DIR", str(tmp_path / "locks"))
|
|
lock_path = tmp_path / "locks" / "telegram-bot-token-2bb80d537b1da3e3.lock"
|
|
lock_path.parent.mkdir(parents=True, exist_ok=True)
|
|
lock_path.write_text(json.dumps({
|
|
"pid": 99999,
|
|
"start_time": 123,
|
|
"kind": "hermes-gateway",
|
|
}))
|
|
|
|
monkeypatch.setattr(status.os, "kill", lambda pid, sig: None)
|
|
monkeypatch.setattr(status, "_get_process_start_time", lambda pid: 123)
|
|
|
|
acquired, existing = status.acquire_scoped_lock("telegram-bot-token", "secret", metadata={"platform": "telegram"})
|
|
|
|
assert acquired is False
|
|
assert existing["pid"] == 99999
|
|
|
|
def test_acquire_scoped_lock_replaces_stale_record(self, tmp_path, monkeypatch):
|
|
monkeypatch.setenv("HERMES_GATEWAY_LOCK_DIR", str(tmp_path / "locks"))
|
|
lock_path = tmp_path / "locks" / "telegram-bot-token-2bb80d537b1da3e3.lock"
|
|
lock_path.parent.mkdir(parents=True, exist_ok=True)
|
|
lock_path.write_text(json.dumps({
|
|
"pid": 99999,
|
|
"start_time": 123,
|
|
"kind": "hermes-gateway",
|
|
}))
|
|
|
|
def fake_kill(pid, sig):
|
|
raise ProcessLookupError
|
|
|
|
monkeypatch.setattr(status.os, "kill", fake_kill)
|
|
|
|
acquired, existing = status.acquire_scoped_lock("telegram-bot-token", "secret", metadata={"platform": "telegram"})
|
|
|
|
assert acquired is True
|
|
payload = json.loads(lock_path.read_text())
|
|
assert payload["pid"] == os.getpid()
|
|
assert payload["metadata"]["platform"] == "telegram"
|
|
|
|
def test_release_scoped_lock_only_removes_current_owner(self, tmp_path, monkeypatch):
|
|
monkeypatch.setenv("HERMES_GATEWAY_LOCK_DIR", str(tmp_path / "locks"))
|
|
|
|
acquired, _ = status.acquire_scoped_lock("telegram-bot-token", "secret", metadata={"platform": "telegram"})
|
|
assert acquired is True
|
|
lock_path = tmp_path / "locks" / "telegram-bot-token-2bb80d537b1da3e3.lock"
|
|
assert lock_path.exists()
|
|
|
|
status.release_scoped_lock("telegram-bot-token", "secret")
|
|
assert not lock_path.exists()
|