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

bolt_pet/config.py

@@ -66,9 +66,38 @@ DEEPGRAM_MODEL = os.environ.get("DEEPGRAM_MODEL", "nova-3")
 ELEVENLABS_API_KEY = os.environ.get("ELEVENLABS_API_KEY", "")
 ELEVENLABS_VOICE_ID = os.environ.get("ELEVENLABS_VOICE_ID", "")
 ELEVENLABS_MODEL_ID = os.environ.get("ELEVENLABS_MODEL_ID", "eleven_flash_v2")
+# eleven_flash_v2 is English-only, and the two cases that swap the voice
+# (server-picked `speak_as`, or a reply with non-ASCII in it) are usually
+# exactly the cases where the reply isn't English — see tts.model_for().
+ELEVENLABS_MULTILINGUAL_MODEL_ID = os.environ.get(
+    "ELEVENLABS_MULTILINGUAL_MODEL_ID", "eleven_flash_v2_5"
+)
 # ElevenLabs PCM output formats are named pcm_<sample_rate>.
 TTS_SAMPLE_RATE = int(os.environ.get("TTS_SAMPLE_RATE", "24000"))
 
+# Does a voice the server picks (its speak_as marker — "talk like a pirate",
+# "say that in Japanese") stay on for later replies, or last one reply only?
+# Sticky by default: the server tags a single reply and does *not* keep the
+# voice id in its history, so a one-reply-only voice can't be re-used when
+# you say "keep talking like that" — it would have to search for a voice
+# again. Reset it from the tray ("Use default voice") or by restarting.
+VOICE_STICKY = os.environ.get("VOICE_STICKY", "true").lower() in ("1", "true", "yes", "on")
+
+# ── multi-voice dialogue (ElevenLabs Text to Dialogue) ──────────────────────
+# Lets Bolt play a short scene in several voices with delivery tags the v3
+# model acts on ("[cheerfully] Hello"), instead of one voice reading a line.
+# Driven by the server through the `dialoguectl` relayed command — see
+# dialogue.py. Costs a separate (slower, whole-clip) request per scene, so
+# it's a set piece, not the normal reply path.
+#
+# DIALOGUE_VOICES names the cast: "narrator:9BWtsMINqrJLrRacOk9x,villain:IKne3meq5aSn9XLyUdCD".
+# The name "self" always resolves to the voice the pet is currently using,
+# including one the server picked with speak_as.
+
+DIALOGUE = os.environ.get("DIALOGUE", "true").lower() in ("1", "true", "yes", "on")
+DIALOGUE_MODEL_ID = os.environ.get("DIALOGUE_MODEL_ID", "eleven_v3")
+DIALOGUE_VOICES = os.environ.get("DIALOGUE_VOICES", "")
+
 # ── mic / VAD (same tuning knobs as bolt_desk.py) ───────────────────────────
 
 MIC_DEVICE = os.environ.get("MIC_DEVICE", "") or None  # sounddevice name/index
@@ -91,7 +120,7 @@ GRACE_SECONDS = float(os.environ.get("VAD_GRACE_SECONDS", "4"))
 # keeps feeding it noise. 0 means no cap.
 
 FOLLOW_UP_LISTEN = os.environ.get("FOLLOW_UP_LISTEN", "true").lower() in ("1", "true", "yes", "on")
-FOLLOW_UP_MAX_TURNS = int(os.environ.get("FOLLOW_UP_MAX_TURNS", "3"))
+FOLLOW_UP_MAX_TURNS = int(os.environ.get("FOLLOW_UP_MAX_TURNS", "10"))
 FOLLOW_UP_GRACE_SECONDS = float(os.environ.get("FOLLOW_UP_GRACE_SECONDS", "7"))
 
 COMMAND_TIMEOUT_SECONDS = int(os.environ.get("COMMAND_TIMEOUT_SECONDS", "30"))
@@ -110,6 +139,14 @@ SUDO_ASKPASS_HELPER = os.environ.get("SUDO_ASKPASS_HELPER", "")  # blank = auto-
 SUDO_COMMAND_TIMEOUT_SECONDS = int(os.environ.get("SUDO_COMMAND_TIMEOUT_SECONDS", "180"))
 HEARTBEAT_INTERVAL_SECONDS = float(os.environ.get("HEARTBEAT_INTERVAL_SECONDS", "60"))
 
+# ── self-restart ────────────────────────────────────────────────────────────
+# `petctl self_restart` lets Bolt restart the pet after editing its code, so
+# he can see his own change running instead of waiting for someone to restart
+# it by hand. The code is import-checked in a subprocess first, and the reason
+# is carried across the restart so the new process can report back — see
+# self_restart.py. SELF_RESTART_MAX/_WINDOW_SECONDS bound the crash-loop case.
+SELF_RESTART = os.environ.get("SELF_RESTART", "true").lower() in ("1", "true", "yes", "on")
+
 # ── barge-in (interrupt playback while the pet is talking) ──────────────────
 # The mic stays live while the pet talks. BARGE_IN_MODE decides what counts
 # as an interruption: