feat: add seamless text and voice chat

agent/agent.py

@@ -80,7 +80,8 @@ SYSTEM_PROMPT = textwrap.dedent("""\
       no markdown, and no formatting except the Azure delivery markers below.
     - Spell out numbers when it sounds more natural ("twenty twenty-six"
       instead of "2026").
-    - If you need to ask a question, ask exactly one.
+    - Make reasonable assumptions and answer directly. Ask a follow-up only
+      when it is genuinely impossible to proceed without one.
     - Be warm and direct. Don't be sycophantic or overly formal.
     - If you don't know something, say so briefly and move on.
 
@@ -144,7 +145,7 @@ SYSTEM_PROMPT = textwrap.dedent("""\
     - User says "look up the price of a PS5" → CALL dispatch_task with
       description="Find the current retail price of a PlayStation 5"
     After calling dispatch_task, tell the user "I'll get on that for you"
-    and keep the conversation going. The result comes back automatically — when
+    without asking for more permission or details. The result comes back automatically — when
     you receive it, share the findings naturally in your conversational style.
     You can have multiple tasks running at once.
 
@@ -612,29 +613,41 @@ async def handle_job(ctx: JobContext) -> None:
         ),
     )
 
-    # Listen for data messages (voice switching) from the web UI.
+    # Listen for conversation controls (voice selection and voice/text mode).
     # Defined here so it captures this job's session via closure.
     def _on_room_data(packet) -> None:
         topic = getattr(packet, "topic", None)
-        if topic and topic != "voice-control":
+        if topic and topic not in ("voice-control", "conversation-control"):
             return
         try:
             msg = json.loads(packet.data.decode("utf-8"))
         except (json.JSONDecodeError, UnicodeDecodeError):
             return
-        if msg.get("type") != "set_voice":
+
+        if msg.get("type") == "set_mode":
+            mode = msg.get("mode")
+            if mode not in ("voice", "text"):
+                return
+            voice_enabled = mode == "voice"
+            logger.info("Switching conversation mode to %s", mode)
+            if not voice_enabled:
+                asyncio.create_task(session.interrupt())
+            session.input.set_audio_enabled(voice_enabled)
+            session.output.set_audio_enabled(voice_enabled)
             return
-        voice = msg.get("voice", "")
-        if not voice:
-            return
-        logger.info("Switching TTS voice to %s", voice)
-        try:
-            tts = session.tts
-            if hasattr(tts, "update_options"):
-                tts.update_options(voice=voice)
-                logger.info("Voice updated to %s", voice)
-        except Exception as e:  # noqa: BLE001
-            logger.warning("Failed to update voice: %s", e)
+
+        if msg.get("type") == "set_voice":
+            voice = msg.get("voice", "")
+            if not voice:
+                return
+            logger.info("Switching TTS voice to %s", voice)
+            try:
+                active_tts = session.tts
+                if hasattr(active_tts, "update_options"):
+                    active_tts.update_options(voice=voice)
+                    logger.info("Voice updated to %s", voice)
+            except Exception as e:  # noqa: BLE001
+                logger.warning("Failed to update voice: %s", e)
 
     ctx.room.on("data_received", _on_room_data)