Send medium reasoning effort through extra body

README.md

@@ -89,7 +89,7 @@ presence_penalty: 0.0
 repetition_penalty: 1.0
 ```
 
-For multi-turn agents, preserve `reasoning_content` between tool turns and keep `preserve_thinking` enabled. Use `reasoning_effort = "medium"` as the general-purpose default. It retains native thinking without the extra system instruction added by the `xhigh` template tier. Reserve `xhigh` for unusually difficult tasks where the additional latency and reasoning tokens are justified.
+For multi-turn agents, preserve `reasoning_content` between tool turns and keep `preserve_thinking` enabled. Use `reasoning_effort = "medium"` inside `extra_body` as the general-purpose default. It retains native thinking without the extra system instruction added by the `xhigh` template tier. It is a prompt policy, not a hard reasoning-token budget. Reserve `xhigh` for unusually difficult tasks where the additional latency and reasoning tokens are justified.
 
 ## Swival setup
 
@@ -105,10 +105,11 @@ max_context_tokens = 131072
 max_output_tokens = 32768
 temperature = 1.0
 top_p = 0.95
-reasoning_effort = "medium"
-extra_body = { top_k = 20, min_p = 0.0, presence_penalty = 0.0, repetition_penalty = 1.0, chat_template_kwargs = { enable_thinking = true, preserve_thinking = true } }
+extra_body = { reasoning_effort = "medium", top_k = 20, min_p = 0.0, presence_penalty = 0.0, repetition_penalty = 1.0, chat_template_kwargs = { enable_thinking = true, preserve_thinking = true } }
 ```
 
+For this unregistered local model, Swival 1.0.41's top-level `reasoning_effort` is removed by LiteLLM's unsupported-parameter filter. Keeping the value inside `extra_body` sends the dedicated OpenAI-compatible field to oMLX. The field is named `reasoning_effort`; `thinking_effort` is not supported by this stack.
+
 Run a task from its workspace so Swival can apply the intended filesystem and command boundaries:
 
 ```sh