fix: catch helper timeouts in run(); report probed state when a command fails

run() now turns subprocess.TimeoutExpired into rc=124, so the poll loop and
on_connect can no longer die on a stalled lgtv.sh (34adf28 only guarded the
command path). A failed ON/OFF publishes a fresh status probe instead of the
requested state. Payload decode uses errors="replace"; safe_handle (34adf28)
already kept bad bytes from killing paho's thread.

tests/test_bridge.py replays the reviewer's three repros.

Fixes-finding: uncaught-helper-timeout-stops-bridge
Fixes-finding: failed-power-commands-publish-success-state
Fixes-finding: malformed-mqtt-payload-kills-network-loop

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

lgtv_mqtt.py

@@ -44,9 +44,15 @@ log = logging.getLogger(__name__)
 
 
 def run(cmd, timeout=60):
+    # Every caller (poll loop, on_connect, commands) routes through here, so a
+    # stalled helper becomes a plain failure instead of an exception.
+    try:
         result = subprocess.run(
             cmd, shell=True, capture_output=True, text=True, timeout=timeout
         )
+    except subprocess.TimeoutExpired:
+        log.warning(f"timed out after {timeout}s: {cmd}")
+        return "timeout", 124
     return result.stdout.strip(), result.returncode
 
 
@@ -129,23 +135,31 @@ def safe_handle(client, msg):
 
 
 def handle_command(client, msg):
-    command = msg.payload.decode().strip().upper()
+    command = msg.payload.decode(errors="replace").strip().upper()
     log.info(f"Received command: {command}")
 
     if command == "ON":
-        tv_on()
+        ok = tv_on()
+    elif command == "OFF":
+        ok = tv_off()
+    else:
+        log.warning(f"Unknown command: {command}")
+        return
+
+    if not ok:
+        # Failed command: report what the TV actually is, not what was asked.
+        state = get_tv_state()
+        client.publish(STATE_TOPIC, state, retain=True)
+        log.warning(f"{command} failed; published probed state: {state}")
+    elif command == "ON":
         # Publish ON optimistically immediately — WoL takes ~20s to appear on network.
         # The 30s poll loop will correct it if it failed.
         client.publish(STATE_TOPIC, "ON", retain=True)
         log.info("State published: ON (optimistic)")
-    elif command == "OFF":
+    else:
-        tv_off()
         time.sleep(3)
         client.publish(STATE_TOPIC, "OFF", retain=True)
         log.info("State published: OFF")
-    else:
-        log.warning(f"Unknown command: {command}")
-        return
 
 
 def main():

tests/test_bridge.py

@@ -0,0 +1,54 @@
+"""Regression checks for the 3 hermes reviewer findings. No broker, no TV.
+Run: python3 tests/test_bridge.py"""
+import subprocess
+from pathlib import Path
+from types import SimpleNamespace
+
+import paho.mqtt.client as mqtt
+
+SRC = Path(__file__).resolve().parents[1] / "lgtv_mqtt.py"
+
+
+def load(run):
+    ns = {"__name__": "test"}
+    exec(compile(SRC.read_text(), str(SRC), "exec"), ns)
+    ns["run"] = run
+    ns["time"] = SimpleNamespace(sleep=lambda _: None)
+    return ns
+
+
+def command(ns, payload):
+    sent = []
+    client = SimpleNamespace(publish=lambda topic, p, retain=False: sent.append(p))
+    ns["handle_command"](client, SimpleNamespace(payload=payload))
+    return sent
+
+
+# failed-power-commands-publish-success-state: on/off fail, TV really still ON
+ns = load(lambda cmd, **k: ("TV: ON", 0) if cmd.endswith("status") else ("", 1))
+assert command(ns, b"OFF") == ["ON"], "failed OFF must not report OFF"
+ns = load(lambda cmd, **k: ("TV: OFF", 0) if cmd.endswith("status") else ("", 1))
+assert command(ns, b"ON") == ["OFF"], "failed ON must not report ON"
+ns = load(lambda cmd, **k: ("", 0))
+assert command(ns, b"ON") == ["ON"] and command(ns, b"OFF") == ["OFF"]
+
+# uncaught-helper-timeout-stops-bridge: real run(), helper that outlives timeout
+ns = {"__name__": "test"}
+exec(compile(SRC.read_text(), str(SRC), "exec"), ns)
+assert ns["run"]("sleep 5", timeout=0.2) == ("timeout", 124)
+ns["LGTV_SCRIPT"] = "sleep 5;"
+ns["run"].__defaults__ = (0.2,)
+assert ns["get_tv_state"]() == "OFF"
+
+# malformed-mqtt-payload-kills-network-loop: real paho dispatch survives
+ns = load(lambda cmd, **k: ("", 0))
+client = mqtt.Client(client_id="test-no-network")
+client.on_message = ns["on_message"]
+msg = mqtt.MQTTMessage()
+msg.topic = b"lgtv/switch/command"
+msg.payload = b"\xff"
+client._handle_on_message(msg)
+ns["worker"].shutdown(wait=True)
+assert command(ns, b"\xff") == []  # decoded, logged as unknown, ignored
+
+print("ok")