Pin llama-server reasoning_effort to low to fix Jinja template error

LangChain was sending reasoning_effort=thinking which Qwen3's chat
template rejects (only xhigh/medium/low are valid). low disables
thinking mode, which is appropriate for agentic tool use and saves tokens.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

blueprints/conversation/agents.py

@@ -39,6 +39,7 @@ if llama_url:
         model=os.getenv("LLAMA_MODEL_NAME", "llama-3.1-8b-instruct"),
         timeout=httpx.Timeout(LLAMA_READ_TIMEOUT, connect=10.0),
         max_retries=1,
+        model_kwargs={"reasoning_effort": "low"},
     )
 else:
     llama_chat = None