refactor(ai_client): _send_llama_native_result() returns Result[str]

src/ai_client.py

@@ -2536,14 +2536,15 @@ def ollama_chat(
  resp = requests.post(f"{base_url}/api/chat", json=payload, timeout=120)
  return resp.json()
 
-def _send_llama_native(md_content: str, user_message: str, base_dir: str,
+def _send_llama_native_result(md_content: str, user_message: str, base_dir: str,
  file_items: list[dict[str, Any]] | None = None,
  discussion_history: str = "",
  stream: bool = False,
  pre_tool_callback: Optional[Callable[[str, str, Optional[Callable[[str], str]]], Optional[str]]] = None,
  qa_callback: Optional[Callable[[str], str]] = None,
  stream_callback: Optional[Callable[[str], None]] = None,
- patch_callback: Optional[Callable[[str, str], Optional[str]]] = None) -> str:
+ patch_callback: Optional[Callable[[str, str], Optional[str]]] = None) -> Result[str]:
+ try:
   base_url = _llama_base_url.replace("/v1", "")
   with _llama_history_lock:
    if discussion_history and not _llama_history:
@@ -2565,7 +2566,9 @@ def _send_llama_native(md_content: str, user_message: str, base_dir: str,
    if thinking:
     msg["thinking"] = thinking
    _llama_history.append(msg)
- return (f"<thinking>\n{thinking}\n</thinking>\n" if thinking else "") + text
+  return Result(data=(f"<thinking>\n{thinking}\n</thinking>\n" if thinking else "") + text)
+ except Exception as exc:
+  return Result(data="", errors=[ErrorInfo(kind=ErrorKind.INTERNAL, message=str(exc), source="ai_client.llama_native", original=exc)])
 def _list_llama_models() -> list[str]:
  from src.vendor_capabilities import list_models_for_vendor
  return list_models_for_vendor("llama")