Fix speech text truncation bug where Assistant: prefix caused multi-line responses to drop remaining sentences

ollama_llm.py

@@ -42,8 +42,10 @@ def _clean_spoken_text(text: str) -> str:
     """Clean text for speech output and truncate fake turn generations."""
     if not text:
         return ""
-    # Truncate if model hallucinates fake turn markers
-    for marker in ("User:", "Human:", "Assistant:", "\nUser", "\nHuman", "\nAssistant"):
+    # Strip leading or inline role headers (e.g. "Assistant:")
+    text = re.sub(r"(?i)\b(Assistant|assistant|Bot|bot):\s*", "", text)
+    # Truncate if model hallucinates fake subsequent user turns
+    for marker in ("\nUser:", "\nHuman:", "\nUser", "\nHuman"):
         if marker in text:
             text = text.split(marker)[0]
     # Remove markdown code blocks