feat: real-time reasoning speech, dynamic voice tags, and unified web UI bubbles

apple_llm.py

@@ -169,9 +169,9 @@ class MacOSLLM(FrameProcessor):
     async def _connect(self):
         available, reason = probe_apple_llm()
         logger.info(f"macOS LLM engine: {reason}")
-        if LLM_HELPER_PATH.exists() and "FoundationModels available" in reason:
+        if LLM_HELPER_PATH.exists() and available and ("FoundationModels" in reason or "Apple Intelligence" in reason):
             self._use_swift = True
-            logger.info("Using Swift FoundationModels engine.")
+            logger.info("Using native Swift macOS Apple Intelligence / FoundationModels engine.")
         else:
             self._use_swift = False
             logger.info(f"Loading MLX model {self._model_name} on Apple Silicon...")
@@ -199,6 +199,9 @@ class MacOSLLM(FrameProcessor):
         await self.cancel_task(task)
 
     async def _run_turn(self, utterance: str):
+        if not self._use_swift and (self._mlx_model is None or self._mlx_tokenizer is None):
+            await self._connect()
+
         self._history.append({"role": "user", "content": utterance})
 
         await self.push_frame(LLMFullResponseStartFrame())
@@ -224,6 +227,10 @@ class MacOSLLM(FrameProcessor):
                             chunk = data["delta"]
                             chunks.append(chunk)
                             await self.push_frame(LLMTextFrame(chunk))
+                        elif "content" in data and not chunks:
+                            chunk = data["content"]
+                            chunks.append(chunk)
+                            await self.push_frame(LLMTextFrame(chunk))
                         elif "text" in data and not chunks:
                             chunk = data["text"]
                             chunks.append(chunk)