Add text-to-dialogue, self-restart capability, and misc updates

tests/test_controller_features.py

@@ -15,6 +15,7 @@ from PySide6.QtWidgets import QApplication
 
 from bolt_pet import controller as controller_mod
 from bolt_pet.notifications import Notification
+from bolt_pet.server_client import Reply
 from bolt_pet.state import PetState
 
 sys.path.insert(0, str(Path(__file__).resolve().parent.parent))
@@ -159,7 +160,7 @@ def test_the_interrupt_log_reports_what_fired_not_the_reset_counters(monkeypatch
     ctrl._barge_in = detector
     logs = _capture(ctrl.log)
 
-    def interrupted_playback(text, on_error=None, should_stop=None):
+    def interrupted_playback(text, on_error=None, should_stop=None, voice_id=None):
         # What really happens: frames get scored during playback, then one
         # clears the threshold and playback aborts.
         detector._frames, detector._peak, detector._last = 7, 0.81, 0.81
@@ -179,7 +180,7 @@ def test_the_interrupt_log_reports_what_fired_not_the_reset_counters(monkeypatch
 def test_interrupted_playback_queues_an_immediate_next_turn(monkeypatch, ctrl):
     logs = _capture(ctrl.log)
     monkeypatch.setattr(controller_mod.tts, "speak",
-                        lambda text, on_error=None, should_stop=None: False)  # interrupted
+                        lambda text, on_error=None, should_stop=None, voice_id=None: False)  # interrupted
 
     ctrl._speak("a very long explanation")
 
@@ -189,7 +190,7 @@ def test_interrupted_playback_queues_an_immediate_next_turn(monkeypatch, ctrl):
 
 def test_uninterrupted_playback_does_not_queue_a_turn(monkeypatch, ctrl):
     monkeypatch.setattr(controller_mod.tts, "speak",
-                        lambda text, on_error=None, should_stop=None: True)
+                        lambda text, on_error=None, should_stop=None, voice_id=None: True)
     ctrl._speak("short answer")
     assert not ctrl._talk_now.is_set()
 
@@ -201,7 +202,7 @@ def spoke(monkeypatch):
     """Playback that always completes, so only the follow-up rule decides
     whether another turn is queued."""
     monkeypatch.setattr(controller_mod.tts, "speak",
-                        lambda text, on_error=None, should_stop=None: True)
+                        lambda text, on_error=None, should_stop=None, voice_id=None: True)
 
 
 def test_a_reply_ending_in_a_question_keeps_listening(spoke, ctrl):
@@ -289,7 +290,7 @@ def test_follow_up_can_be_turned_off(spoke, monkeypatch, ctrl):
 
 def test_being_interrupted_restarts_the_chain(monkeypatch, ctrl):
     monkeypatch.setattr(controller_mod.tts, "speak",
-                        lambda text, on_error=None, should_stop=None: False)
+                        lambda text, on_error=None, should_stop=None, voice_id=None: False)
     ctrl._follow_ups = 3
 
     ctrl._speak("a very long explanation")
@@ -300,7 +301,7 @@ def test_being_interrupted_restarts_the_chain(monkeypatch, ctrl):
 
 def test_speech_is_recorded_in_the_history(monkeypatch, ctrl):
     monkeypatch.setattr(controller_mod.tts, "speak",
-                        lambda text, on_error=None, should_stop=None: True)
+                        lambda text, on_error=None, should_stop=None, voice_id=None: True)
     ctrl._speak("**bold** reply")
     assert ctrl.history.last().text == "**bold** reply"  # raw, for copy/paste
 
@@ -314,10 +315,10 @@ def test_the_active_window_rides_along_with_the_utterance(monkeypatch, ctrl):
     monkeypatch.setattr(controller_mod.screen_context, "context_for",
                         lambda text: f"{text}\n\n[on screen right now: app.py]")
     monkeypatch.setattr(controller_mod.tts, "speak",
-                        lambda text, on_error=None, should_stop=None: True)
+                        lambda text, on_error=None, should_stop=None, voice_id=None: True)
     sent = []
     monkeypatch.setattr(controller_mod.server_client, "converse",
-                        lambda text, on_command=None: sent.append(text) or "that's a KeyError")
+                        lambda text, on_command=None: sent.append(text) or Reply("that's a KeyError"))
 
     ctrl._handle_conversation_turn()
 
@@ -370,10 +371,10 @@ def test_napping_still_answers_when_spoken_to(monkeypatch, ctrl):
                         lambda *a, **k: np.zeros(10, dtype=np.int16))
     monkeypatch.setattr(controller_mod.stt, "transcribe", lambda pcm: "you awake?")
     monkeypatch.setattr(controller_mod.server_client, "converse",
-                        lambda text, on_command=None: "always")
+                        lambda text, on_command=None: Reply("always"))
     spoken = []
     monkeypatch.setattr(controller_mod.tts, "speak",
-                        lambda text, on_error=None, should_stop=None: spoken.append(text) or True)
+                        lambda text, on_error=None, should_stop=None, voice_id=None: spoken.append(text) or True)
     ctrl.set_napping(True)
 
     ctrl._handle_conversation_turn()
@@ -388,9 +389,9 @@ def test_notifications_are_forwarded_and_spoken(monkeypatch, ctrl):
     ctrl._notification_gate = controller_mod.notifications.NotificationGate("", 0)
     sent, spoken = [], []
     monkeypatch.setattr(controller_mod.server_client, "converse",
-                        lambda text, on_command=None: sent.append(text) or "your build is green")
+                        lambda text, on_command=None: sent.append(text) or Reply("your build is green"))
     monkeypatch.setattr(controller_mod.tts, "speak",
-                        lambda text, on_error=None, should_stop=None: spoken.append(text) or True)
+                        lambda text, on_error=None, should_stop=None, voice_id=None: spoken.append(text) or True)
 
     ctrl._queue_notification(Notification(app="CI", summary="Build finished", body=""))
     ctrl._drain_notifications()
@@ -506,9 +507,9 @@ def test_check_deliveries_runs_after_a_conversation_turn(monkeypatch, ctrl, tmp_
                         lambda *a, **k: np.zeros(10, dtype=np.int16))
     monkeypatch.setattr(controller_mod.stt, "transcribe", lambda pcm: "send me that file")
     monkeypatch.setattr(controller_mod.server_client, "converse",
-                        lambda text, on_command=None: "it's on the way")
+                        lambda text, on_command=None: Reply("it's on the way"))
     monkeypatch.setattr(controller_mod.tts, "speak",
-                        lambda text, on_error=None, should_stop=None: True)
+                        lambda text, on_error=None, should_stop=None, voice_id=None: True)
     monkeypatch.setattr(controller_mod.config, "DELIVERED_FILES_DIR", tmp_path)
     monkeypatch.setattr(controller_mod.server_client, "list_outbox_files",
                         lambda: [{"id": "abc", "name": "notes.txt", "size": 2}])
@@ -518,3 +519,294 @@ def test_check_deliveries_runs_after_a_conversation_turn(monkeypatch, ctrl, tmp_
     ctrl._handle_conversation_turn()
 
     assert (tmp_path / "notes.txt").read_bytes() == b"hi"
+
+
+# ── server-picked voice (the desk API's speak_as marker) ────────────────────
+
+def _voice_turn(monkeypatch, ctrl, reply, said="talk like a pirate"):
+    """Run one full conversation turn whose reply is *reply*, returning the
+    voice_id each tts.speak() call was given."""
+    voices = []
+    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)
+    monkeypatch.setattr(controller_mod.server_client, "converse",
+                        lambda text, on_command=None: reply)
+    monkeypatch.setattr(
+        controller_mod.tts, "speak",
+        lambda text, on_error=None, should_stop=None, voice_id=None:
+            voices.append(voice_id) or True,
+    )
+    ctrl._handle_conversation_turn()
+    return voices
+
+
+def test_a_speak_as_reply_is_spoken_in_that_voice(monkeypatch, ctrl):
+    voices = _voice_turn(monkeypatch, ctrl, Reply("Ahoy.", "VOICE1", "Terence"))
+    assert voices == ["VOICE1"]
+    assert ctrl.current_voice() == "Terence"
+
+
+def test_the_picked_voice_sticks_for_later_replies(monkeypatch, ctrl):
+    """The server tags one reply and doesn't keep the id in its history, so
+    it can't re-request the voice when you say "keep talking like that"."""
+    monkeypatch.setattr(controller_mod.config, "VOICE_STICKY", True)
+    _voice_turn(monkeypatch, ctrl, Reply("Ahoy.", "VOICE1", "Terence"))
+    voices = _voice_turn(monkeypatch, ctrl, Reply("Still me."), said="and now?")
+    assert voices == ["VOICE1"]
+
+
+def test_voice_stickiness_can_be_turned_off(monkeypatch, ctrl):
+    monkeypatch.setattr(controller_mod.config, "VOICE_STICKY", False)
+    _voice_turn(monkeypatch, ctrl, Reply("Ahoy.", "VOICE1", "Terence"))
+    voices = _voice_turn(monkeypatch, ctrl, Reply("Back to normal."), said="and now?")
+    assert voices == [None]
+    assert ctrl.current_voice() == ""
+
+
+def test_a_new_pick_replaces_the_old_one(monkeypatch, ctrl):
+    changes = _capture(ctrl.voice_changed)
+    _voice_turn(monkeypatch, ctrl, Reply("Ahoy.", "VOICE1", "Terence"))
+    voices = _voice_turn(monkeypatch, ctrl, Reply("こんにちは。", "VOICE2", "Asahi"),
+                         said="say that in Japanese")
+    assert voices == ["VOICE2"]
+    assert changes == ["Terence", "Asahi"]
+
+
+def test_resetting_the_voice_goes_back_to_the_default(monkeypatch, ctrl):
+    _voice_turn(monkeypatch, ctrl, Reply("Ahoy.", "VOICE1", "Terence"))
+    changes = _capture(ctrl.voice_changed)
+
+    ctrl.reset_voice()
+
+    assert ctrl.current_voice() == ""
+    assert changes == [""]  # the tray's menu entry follows this signal
+    voices = _voice_turn(monkeypatch, ctrl, Reply("Normal again."), said="hi")
+    assert voices == [None]
+
+
+def test_an_unnamed_voice_still_reports_something_resettable(monkeypatch, ctrl):
+    """voice_name is optional server-side — falling back to the id keeps the
+    tray entry from reading "now: " with nothing after it."""
+    _voice_turn(monkeypatch, ctrl, Reply("Ahoy.", "VOICE1"))
+    assert ctrl.current_voice() == "VOICE1"
+
+
+def test_petctl_voice_reset_returns_bolt_to_his_own_voice(monkeypatch, ctrl):
+    """The server can pick a voice but can't ask for the default back — it
+    was never told what Bolt's own voice id is. This is how it asks."""
+    ran = []
+    monkeypatch.setattr(controller_mod.server_client, "run_local_command", lambda cmd: ran.append(cmd))
+    _voice_turn(monkeypatch, ctrl, Reply("Ahoy.", "VOICE1", "Terence"))
+
+    output = ctrl._handle_command("petctl voice reset")
+
+    assert ran == []  # never reaches a shell, like every other petctl verb
+    assert "Terence" in output  # the server can't see the voice; tell it what changed
+    assert ctrl.current_voice() == ""
+    assert _voice_turn(monkeypatch, ctrl, Reply("Normal again."), said="hi") == [None]
+
+
+def test_petctl_voice_reset_says_so_when_there_was_nothing_to_reset(ctrl):
+    assert "already" in ctrl._handle_command("petctl voice reset")
+
+
+# ── dialoguectl (multi-voice scenes) ────────────────────────────────────────
+
+def _dialogue_command(*lines):
+    import json
+    return "dialoguectl " + json.dumps({"lines": list(lines)})
+
+
+def test_dialoguectl_never_reaches_the_shell(monkeypatch, ctrl):
+    ran = []
+    monkeypatch.setattr(controller_mod.server_client, "run_local_command", lambda cmd: ran.append(cmd))
+    monkeypatch.setattr(controller_mod.config, "ELEVENLABS_VOICE_ID", "aaorr6ZHIL88gEexu7dC")
+    monkeypatch.setattr(controller_mod.tts, "synthesize_dialogue",
+                        lambda inputs, model_id=None, stability=None: (np.zeros(4, dtype=np.int16), 24000))
+    monkeypatch.setattr(controller_mod.tts, "play_pcm",
+                        lambda pcm, rate, should_stop=None: True)
+
+    output = ctrl._handle_command(_dialogue_command({"voice": "self", "text": "[cheerfully] hi"}))
+
+    assert ran == []
+    assert "[dialogue] played 1 line" in output
+
+
+def test_a_scene_shows_in_the_bubble_with_the_delivery_tags_stripped(monkeypatch, ctrl):
+    monkeypatch.setattr(controller_mod.config, "ELEVENLABS_VOICE_ID", "aaorr6ZHIL88gEexu7dC")
+    monkeypatch.setattr(controller_mod.config, "DIALOGUE_VOICES", "narrator:9BWtsMINqrJLrRacOk9x")
+    monkeypatch.setattr(controller_mod.tts, "synthesize_dialogue",
+                        lambda inputs, model_id=None, stability=None: (np.zeros(4, dtype=np.int16), 24000))
+    monkeypatch.setattr(controller_mod.tts, "play_pcm", lambda pcm, rate, should_stop=None: True)
+    said = _capture(ctrl.said)
+
+    ctrl._handle_command(_dialogue_command(
+        {"voice": "self", "text": "[cheerfully] Hello there!"},
+        {"voice": "narrator", "text": "[whispering] He is lying."},
+    ))
+
+    assert said == ["Hello there! He is lying."]
+    assert ctrl.history.last().text == "Hello there! He is lying."
+
+
+def test_a_mid_turn_scene_returns_to_thinking_not_idle(monkeypatch, ctrl):
+    """The server is still waiting on the tool result, so the pet talks and
+    goes back to waiting — dropping to IDLE would look like the turn ended."""
+    monkeypatch.setattr(controller_mod.config, "ELEVENLABS_VOICE_ID", "aaorr6ZHIL88gEexu7dC")
+    monkeypatch.setattr(controller_mod.tts, "synthesize_dialogue",
+                        lambda inputs, model_id=None, stability=None: (np.zeros(4, dtype=np.int16), 24000))
+    monkeypatch.setattr(controller_mod.tts, "play_pcm", lambda pcm, rate, should_stop=None: True)
+    ctrl._state.transition(PetState.LISTENING)
+    ctrl._state.transition(PetState.THINKING)
+    states = _capture(ctrl.state_changed)
+
+    ctrl._handle_command(_dialogue_command({"voice": "self", "text": "hi"}))
+
+    assert states == ["talking", "thinking"]
+    assert ctrl._state.state == PetState.THINKING
+
+
+def test_the_scene_uses_a_voice_the_server_picked_with_speak_as(monkeypatch, ctrl):
+    monkeypatch.setattr(controller_mod.config, "ELEVENLABS_VOICE_ID", "aaorr6ZHIL88gEexu7dC")
+    seen = {}
+
+    def capture(inputs, model_id=None, stability=None):
+        seen["inputs"] = inputs
+        return np.zeros(4, dtype=np.int16), 24000
+
+    monkeypatch.setattr(controller_mod.tts, "synthesize_dialogue", capture)
+    monkeypatch.setattr(controller_mod.tts, "play_pcm", lambda pcm, rate, should_stop=None: True)
+    ctrl._apply_voice(controller_mod.server_client.Reply("ok", "PICKEDvoice123456789", "Terence"))
+
+    ctrl._handle_command(_dialogue_command({"voice": "self", "text": "hi"}))
+
+    assert seen["inputs"][0]["voice_id"] == "PICKEDvoice123456789"
+
+
+def test_a_synthesis_failure_is_reported_back_for_bolt_to_retry(monkeypatch, ctrl):
+    monkeypatch.setattr(controller_mod.config, "ELEVENLABS_VOICE_ID", "aaorr6ZHIL88gEexu7dC")
+
+    def boom(inputs, model_id=None, stability=None):
+        raise controller_mod.tts.TtsError("voice_id not found")
+
+    monkeypatch.setattr(controller_mod.tts, "synthesize_dialogue", boom)
+
+    output = ctrl._handle_command(_dialogue_command({"voice": "self", "text": "hi"}))
+
+    assert "couldn't synthesize" in output and "voice_id not found" in output
+    assert ctrl._state.state == PetState.IDLE  # nothing left half-transitioned
+
+
+def test_a_bad_voice_name_comes_back_as_advice_not_an_exception(monkeypatch, ctrl):
+    monkeypatch.setattr(controller_mod.config, "DIALOGUE_VOICES", "narrator:9BWtsMINqrJLrRacOk9x")
+    output = ctrl._handle_command(_dialogue_command({"voice": "wizard", "text": "hi"}))
+    assert "unknown voice" in output and "narrator" in output
+
+
+def test_dialogue_can_be_switched_off_on_this_device(monkeypatch, ctrl):
+    monkeypatch.setattr(controller_mod.config, "DIALOGUE", False)
+    called = []
+    monkeypatch.setattr(controller_mod.tts, "synthesize_dialogue",
+                        lambda *a, **k: called.append(1))
+    output = ctrl._handle_command(_dialogue_command({"voice": "self", "text": "hi"}))
+    assert "disabled" in output and called == []
+
+
+def test_talking_over_a_scene_is_reported_up_the_relay(monkeypatch, ctrl):
+    monkeypatch.setattr(controller_mod.config, "ELEVENLABS_VOICE_ID", "aaorr6ZHIL88gEexu7dC")
+    monkeypatch.setattr(controller_mod.tts, "synthesize_dialogue",
+                        lambda inputs, model_id=None, stability=None: (np.zeros(4, dtype=np.int16), 24000))
+    monkeypatch.setattr(controller_mod.tts, "play_pcm",
+                        lambda pcm, rate, should_stop=None: False)  # barge-in
+
+    output = ctrl._handle_command(_dialogue_command({"voice": "self", "text": "hi"}))
+
+    assert "interrupted" in output
+
+
+# ── petctl self_restart ─────────────────────────────────────────────────────
+
+def test_self_restart_arms_after_the_turn_rather_than_dying_mid_relay(monkeypatch, ctrl, tmp_path):
+    """Restarting inline would kill the HTTP tool relay before the result was
+    posted, and the server would wait out its timeout on a turn that can never
+    finish. So the command returns, the turn completes, *then* the pet dies."""
+    monkeypatch.setattr(controller_mod.self_restart, "DEFAULT_STATE_PATH", tmp_path / "ctx.json")
+    monkeypatch.setattr(controller_mod.self_restart, "preflight", lambda *a, **k: None)
+    restarts = _capture(ctrl.restart_requested)
+
+    output = ctrl._handle_command("petctl self_restart check the new dialogue code")
+
+    assert "restarting as soon as this turn finishes" in output
+    assert restarts == []  # nothing has happened yet
+
+    assert ctrl._maybe_self_restart() is True
+    assert restarts and "check the new dialogue code" in restarts[0]
+
+
+def test_a_broken_edit_is_reported_instead_of_leaving_nothing_running(monkeypatch, ctrl, tmp_path):
+    monkeypatch.setattr(controller_mod.self_restart, "DEFAULT_STATE_PATH", tmp_path / "ctx.json")
+
+    def boom(*args, **kwargs):
+        raise controller_mod.self_restart.RestartError(
+            "the current code does not import, so restarting would leave you with "
+            "nothing running. Fix this first:\nSyntaxError: invalid syntax"
+        )
+
+    monkeypatch.setattr(controller_mod.self_restart, "preflight", boom)
+    restarts = _capture(ctrl.restart_requested)
+
+    output = ctrl._handle_command("petctl self_restart try the new code")
+
+    assert "SyntaxError" in output and "refused" in output
+    assert ctrl._maybe_self_restart() is False
+    assert restarts == []
+
+
+def test_a_second_restart_request_in_one_turn_is_a_no_op(monkeypatch, ctrl, tmp_path):
+    monkeypatch.setattr(controller_mod.self_restart, "DEFAULT_STATE_PATH", tmp_path / "ctx.json")
+    monkeypatch.setattr(controller_mod.self_restart, "preflight", lambda *a, **k: None)
+    ctrl._handle_command("petctl self_restart first")
+    assert "already armed" in ctrl._handle_command("petctl self_restart second")
+
+
+def test_self_restart_can_be_switched_off_on_this_device(monkeypatch, ctrl):
+    monkeypatch.setattr(controller_mod.config, "SELF_RESTART", False)
+    checked = []
+    monkeypatch.setattr(controller_mod.self_restart, "preflight",
+                        lambda *a, **k: checked.append(1))
+    assert "disabled" in ctrl._handle_command("petctl self_restart go")
+    assert checked == []
+
+
+def test_coming_back_up_reports_to_the_server_and_speaks_the_reply(monkeypatch, ctrl, tmp_path):
+    """The half that makes it a loop: the new process tells Bolt it's back and
+    why, and his answer is spoken like any other turn."""
+    state = tmp_path / "ctx.json"
+    monkeypatch.setattr(controller_mod.self_restart, "DEFAULT_STATE_PATH", state)
+    controller_mod.self_restart.arm("check the walk cycle", version="0.2.3",
+                                    path=state, now=1000.0)
+    sent, spoken = [], []
+    monkeypatch.setattr(controller_mod.server_client, "converse",
+                        lambda text, on_command=None: sent.append(text) or Reply("Good, it's up."))
+    monkeypatch.setattr(controller_mod.tts, "speak",
+                        lambda text, on_error=None, should_stop=None, voice_id=None:
+                            spoken.append(text) or True)
+
+    ctrl._report_self_restart()
+
+    assert "[pet self-restart]" in sent[0] and "check the walk cycle" in sent[0]
+    assert spoken == ["Good, it's up."]
+    # Consumed, so the next start doesn't announce the same restart again.
+    assert controller_mod.self_restart.load(state) is None
+
+
+def test_an_ordinary_start_reports_nothing(monkeypatch, ctrl, tmp_path):
+    monkeypatch.setattr(controller_mod.self_restart, "DEFAULT_STATE_PATH", tmp_path / "none.json")
+    called = []
+    monkeypatch.setattr(controller_mod.server_client, "converse",
+                        lambda text, on_command=None: called.append(text))
+
+    ctrl._report_self_restart()
+
+    assert called == []