fix: surface reasoning_content when content is empty (thinking models) (#1233)

Thinking models served via llama.cpp without --reasoning-format none
(e.g. Qwen3, DeepSeek-R1) route all tokens into reasoning_content and
return content="". Two call paths were silently broken:

- llm_call / llm_call_async (non-streaming): hard-keyed
  data["choices"][0]["message"]["content"] raises KeyError or returns
  empty string, discarding the entire response.

- stream_agent_loop end-of-round fallback: when full_response is empty
  but round_reasoning has content, the existing code replaced the
  response with the generic empty-response error message, discarding
  all reasoning tokens that were correctly accumulated during streaming.

Fix: in both non-streaming paths use msg.get("content") or
msg.get("reasoning_content") or "". In the streaming fallback, surface
round_reasoning as the answer before falling through to the error path.

src/llm_core.py

@@ -860,7 +860,8 @@ def llm_call(url: str, model: str, messages: List[Dict], temperature: float = LL
         elif provider == "ollama":
             response = _parse_ollama_response(data)
         else:
-            response = data["choices"][0]["message"]["content"]
+            msg = data["choices"][0]["message"]
+            response = msg.get("content") or msg.get("reasoning_content") or ""
         _set_cached_response(cache_key, response)
         return response
     except Exception:
@@ -997,7 +998,8 @@ async def llm_call_async(
                 elif provider == "ollama":
                     response = _parse_ollama_response(data)
                 else:
-                    response = data["choices"][0]["message"]["content"]
+                    msg = data["choices"][0]["message"]
+                    response = msg.get("content") or msg.get("reasoning_content") or ""
                 _set_cached_response(cache_key, response)
                 return response
             except Exception: