feat: Enhance local command handling and introduce local intents

- Refactor `run_local_command` to manage subprocesses more effectively, ensuring child processes are terminated on timeout.
- Introduce `_terminate` function to handle process group termination and capture output.
- Implement `_command_output` to format command results with a character limit.
- Add local intent recognition in `intents.py` to handle commands like "stop", "go to sleep", and "come here" without server interaction.
- Normalize user input to match local intents while stripping filler words.
- Update tests to cover new local intent functionality and ensure proper command handling.
- Enhance speech processing to handle abbreviations and improve spoken output clarity.

tests/test_controller_features.py

@@ -221,10 +221,13 @@ def test_a_statement_does_not_keep_listening(spoke, ctrl):
     assert not ctrl._pending_follow_up
 
 
-def test_a_question_in_passing_does_not_count(spoke, ctrl):
-    """Only a reply that *ends* on a question is waiting for an answer."""
-    ctrl._speak("What time is it? It's 7:15 AM.")
-    assert not ctrl._talk_now.is_set()
+def test_a_question_anywhere_in_the_reply_keeps_listening(spoke, ctrl):
+    """Bolt often asks and then keeps talking ("Want me to fix it? I'd start
+    with the config."), so the question mark doesn't have to be last. An
+    unwanted extra listen ends itself on VAD_GRACE_SECONDS of silence; a missed
+    one costs you a wake word, which is the more expensive mistake."""
+    ctrl._speak("Want me to restart it? It's been up for 40 days.")
+    assert ctrl._talk_now.is_set()
 
 
 def test_follow_ups_stop_at_the_cap(spoke, monkeypatch, ctrl):
@@ -382,6 +385,148 @@ def test_napping_still_answers_when_spoken_to(monkeypatch, ctrl):
     assert spoken == ["always"]
 
 
+# ── local intents ───────────────────────────────────────────────────────────
+
+@pytest.fixture
+def heard(monkeypatch):
+    """A turn where you said something, with the server and TTS recorded.
+    Returns (utterance_setter, sent, spoken)."""
+    said = {"text": ""}
+    sent, spoken = [], []
+    monkeypatch.setattr(controller_mod.mic, "record_utterance",
+                        lambda *a, **k: np.zeros(10, dtype=np.int16))
+    monkeypatch.setattr(controller_mod.stt, "transcribe", lambda pcm: said["text"])
+    monkeypatch.setattr(controller_mod.server_client, "converse",
+                        lambda text, on_command=None: sent.append(text) or Reply("from the server"))
+    monkeypatch.setattr(controller_mod.tts, "speak",
+                        lambda text, on_error=None, should_stop=None, voice_id=None:
+                        spoken.append(text) or True)
+    return said, sent, spoken
+
+
+def test_a_local_intent_never_reaches_the_server(heard, ctrl):
+    said, sent, spoken = heard
+    said["text"] = "come here"
+    actions = _capture(ctrl.action)
+
+    ctrl._handle_conversation_turn()
+
+    assert sent == []                                        # no round trip at all
+    assert actions == [{"action": "move", "anchor": "cursor"}]
+    assert spoken == []                                      # walking over is the reply
+    assert ctrl._state.state == PetState.IDLE
+
+
+def test_stop_is_answered_with_silence(heard, ctrl):
+    said, sent, spoken = heard
+    said["text"] = "be quiet"
+    ctrl._handle_conversation_turn()
+    assert (sent, spoken) == ([], [])
+
+
+def test_a_request_that_merely_starts_with_an_intent_word_goes_to_the_server(heard, ctrl):
+    said, sent, spoken = heard
+    said["text"] = "stop the docker container"
+    ctrl._handle_conversation_turn()
+    assert sent and "stop the docker container" in sent[0]
+    assert spoken == ["from the server"]
+
+
+def test_local_intents_are_skipped_while_answering_a_question(heard, ctrl):
+    """Bolt asked something; "never mind" is an answer to him, not a body
+    command. Swallowing it locally would leave the server holding a question it
+    never got a reply to."""
+    said, sent, spoken = heard
+    said["text"] = "never mind"
+    ctrl._pending_follow_up = True
+
+    ctrl._handle_conversation_turn()
+
+    assert sent and "never mind" in sent[0]
+
+
+def test_local_intents_can_be_turned_off(monkeypatch, heard, ctrl):
+    monkeypatch.setattr(controller_mod.config, "LOCAL_INTENTS", False)
+    said, sent, spoken = heard
+    said["text"] = "come here"
+    ctrl._handle_conversation_turn()
+    assert sent and "come here" in sent[0]
+
+
+def test_say_that_again_replays_the_last_line_without_duplicating_history(heard, ctrl):
+    said, sent, spoken = heard
+    ctrl.history.add(controller_mod.history_mod.PET, "it's 7:15 AM", 0.0)
+    said["text"] = "what did you say?"
+
+    ctrl._handle_conversation_turn()
+
+    assert spoken == ["it's 7:15 AM"]
+    assert sent == []
+    pet_lines = [e.text for e in ctrl.history.entries()
+                 if e.role == controller_mod.history_mod.PET]
+    assert pet_lines == ["it's 7:15 AM"]  # replayed, not re-recorded
+
+
+def test_repeat_with_nothing_to_repeat_says_so(heard, ctrl):
+    said, sent, spoken = heard
+    said["text"] = "say that again"
+    ctrl._handle_conversation_turn()
+    assert spoken == ["I haven't said anything yet."]
+
+
+def test_going_back_to_the_normal_voice_needs_no_server_prompt_support(heard, ctrl):
+    """The server can only offer `petctl voice reset` if its prompt happens to
+    advertise the verb; recognising the phrase here works regardless."""
+    said, sent, spoken = heard
+    ctrl._voice_id, ctrl._voice_name = "voice-123", "Brian"
+    changed = _capture(ctrl.voice_changed)
+    said["text"] = "go back to your normal voice"
+
+    ctrl._handle_conversation_turn()
+
+    assert ctrl._voice_id == ""
+    assert changed == [""]
+    assert spoken == ["Back to my own voice."]
+    assert sent == []
+
+
+def test_go_to_sleep_overrides_the_quiet_hours_schedule(heard, ctrl):
+    said, sent, spoken = heard
+    said["text"] = "go to sleep"
+
+    ctrl._handle_conversation_turn()
+
+    assert ctrl._napping is True
+    assert ctrl._nap_forced is True   # not undone by the next schedule check
+    assert spoken == ["Night."]
+
+
+# ── failure containment ─────────────────────────────────────────────────────
+
+def test_one_bad_turn_does_not_end_the_session(monkeypatch, ctrl):
+    """A turn raising something unforeseen used to unwind _loop and kill the
+    thread — the pet would go deaf until it was restarted by hand."""
+    logs = _capture(ctrl.log)
+
+    def explode():
+        raise RuntimeError("numpy said no")
+
+    assert ctrl._guarded(explode, "conversation turn") is False
+    assert ctrl._state.state == PetState.IDLE
+    assert any("Recovered from a conversation turn failure" in m for m in logs)
+
+
+def test_a_command_handler_crash_is_reported_up_the_relay(monkeypatch, ctrl):
+    """The server is blocked on /desk/tool_result while this runs. Raising would
+    leave it waiting out its own timeout on a turn that can never finish."""
+    monkeypatch.setattr(controller_mod.pet_actions, "parse",
+                        lambda command: (_ for _ in ()).throw(KeyError("boom")))
+
+    output = ctrl._handle_command("petctl move top-left")
+
+    assert output.startswith("[error]") and "boom" in output
+
+
 # ── notification bridge ─────────────────────────────────────────────────────
 
 def test_notifications_are_forwarded_and_spoken(monkeypatch, ctrl):
@@ -404,7 +549,54 @@ def test_notifications_are_forwarded_and_spoken(monkeypatch, ctrl):
 def test_filtered_out_notifications_are_never_queued(ctrl):
     ctrl._notification_gate = controller_mod.notifications.NotificationGate("deploy", 0)
     ctrl._queue_notification(Notification(app="Chat", summary="lunch?", body=""))
-    assert ctrl._pending_notifications == []
+    assert not ctrl._pending_notifications
+
+
+def test_the_notification_queue_is_bounded(monkeypatch, ctrl):
+    """An overnight nap can't grow the queue without limit — the drain only runs
+    from the heartbeat, and the heartbeat doesn't run while napping."""
+    monkeypatch.setattr(controller_mod.config, "NOTIFICATION_QUEUE_LIMIT", 3)
+    ctrl = controller_mod.PetController()
+    ctrl._notification_gate = controller_mod.notifications.NotificationGate("", 0)
+
+    for index in range(10):
+        ctrl._queue_notification(Notification(app="CI", summary=f"build {index}", body=""))
+
+    queued = [notification.summary for _stamp, notification in ctrl._pending_notifications]
+    assert queued == ["build 7", "build 8", "build 9"]  # oldest dropped
+
+
+def test_stale_notifications_are_dropped_instead_of_read_out(monkeypatch, ctrl):
+    monkeypatch.setattr(controller_mod.config, "NOTIFICATION_MAX_AGE_SECONDS", 900)
+    sent = []
+    monkeypatch.setattr(controller_mod.server_client, "converse",
+                        lambda text, on_command=None: sent.append(text) or Reply(""))
+    ctrl._notification_gate = controller_mod.notifications.NotificationGate("", 0)
+    ctrl._queue_notification(Notification(app="CI", summary="fresh", body=""))
+    # Backdate it past the age limit, as an overnight backlog would be.
+    stamp, notification = ctrl._pending_notifications.pop()
+    ctrl._pending_notifications.append((stamp - 4000, notification))
+
+    ctrl._drain_notifications()
+
+    assert sent == []
+
+
+def test_a_nap_starting_mid_drain_keeps_the_rest_queued(monkeypatch, ctrl):
+    """The old code swapped the queue out and returned, losing the remainder."""
+    def converse(text, on_command=None):
+        ctrl._napping = True  # e.g. quiet hours began, or a fullscreen app opened
+        return Reply("")
+
+    monkeypatch.setattr(controller_mod.server_client, "converse", converse)
+    ctrl._notification_gate = controller_mod.notifications.NotificationGate("", 0)
+    for index in range(3):
+        ctrl._queue_notification(Notification(app="CI", summary=f"build {index}", body=""))
+
+    ctrl._drain_notifications()
+
+    remaining = [notification.summary for _stamp, notification in ctrl._pending_notifications]
+    assert remaining == ["build 1", "build 2"]
 
 
 def test_notifications_are_not_forwarded_while_napping(monkeypatch, ctrl):