feat: integrate JV Voice Profile cloning, Voicebox research, and ensure session voice/markdown prompt nudge

hermes_llm.py

@@ -50,6 +50,17 @@ SESSION_ID_REGEX = re.compile(r"\bsession_id:\s*([^\s]+)", re.IGNORECASE)
 
 
 
+VOICE_PROMPT_NUDGE = """[System Instruction / Voice & UI Context:
+You are communicating with the user in a real-time voice conversation over microphone and TTS, while displaying formatted responses in the Companion Web UI.
+- Keep spoken responses natural, concise, and conversational (1-2 sentences per turn unless details are requested).
+- Use clean Markdown formatting (bolding, code blocks, bullet points) for readability in the Web UI.
+- Write text meant to be read aloud using clear, natural phrasing and conversational contractions.
+- Avoid repetitive filler openers like "Certainly!", "Absolutely!", or "Great question!".
+- Perform any required tools or file operations silently without narrating step-by-step internal execution.]
+
+"""
+
+
 def _strip_ansi(text: str) -> str:
     if not text:
         return ""
@@ -220,6 +231,8 @@ class HermesLLM(FrameProcessor):
         # Hermes conversations.
         self._session_state_file = self._cwd / ".hermes-voice-session.json"
 
+        self._nudge_sent = False
+
         # Persisted session ID
         self._session_id: str | None = self._load_session_id()
         if self._session_id:
@@ -230,6 +243,7 @@ class HermesLLM(FrameProcessor):
         logger.info("Resetting active Hermes session state...")
         self._session_id = None
         self._session_renamed = False
+        self._nudge_sent = False
         self._history.clear()
         if self._proc:
             asyncio.create_task(self._stop_persistent_proc())
@@ -246,6 +260,7 @@ class HermesLLM(FrameProcessor):
             logger.info(f"Hermes session state updated from disk: {self._session_id} -> {disk_sid}")
             self._session_id = disk_sid
             self._session_renamed = False
+            self._nudge_sent = False
             self._history.clear()
             if self._proc:
                 asyncio.create_task(self._stop_persistent_proc())
@@ -522,6 +537,11 @@ class HermesLLM(FrameProcessor):
             if not messages or messages[-1].get("content") != utterance:
                 messages.append({"role": "user", "content": utterance})
 
+            if not self._nudge_sent and messages:
+                messages[0]["content"] = VOICE_PROMPT_NUDGE + messages[0]["content"]
+                self._nudge_sent = True
+                logger.info("Injecting voice & markdown interaction context nudge into Hermes session.")
+
             payload = {
                 "model": "hermes-agent" if not self._model or self._model.lower() in ("default", "none", "") else self._model,
                 "messages": messages,
@@ -675,7 +695,14 @@ class HermesLLM(FrameProcessor):
         """Run turn via Hermes CLI using persistent session tracking."""
         if spoken_chunks is None:
             spoken_chunks = chunks
-        cmd = [self._cli_path, "chat", "-q", utterance, "-Q", "--source", "voice", "--reasoning", "none"]
+
+        prompt_to_send = utterance
+        if not self._nudge_sent:
+            prompt_to_send = VOICE_PROMPT_NUDGE + utterance
+            self._nudge_sent = True
+            logger.info("Initializing Hermes turn with voice & markdown interaction context nudge.")
+
+        cmd = [self._cli_path, "chat", "-q", prompt_to_send, "-Q", "--source", "voice"]
         if self._session_id:
             cmd.extend(["-r", self._session_id])
         if self._model and self._model.lower() not in ("default", "none", ""):