inference: support reasoning effort for openrouter

backend/src/inference.py

@@ -353,6 +353,14 @@ async def openrouter_chat_completion(app, messages, model, tools=[], opts={}, ag
         if formatted_tools:
             kwargs['tools'] = formatted_tools
 
+        temp = agent_run.input.get("temperature")
+        if temp is not None:
+            kwargs['temperature'] = temp
+
+        reasoning = agent_run.input.get("reasoning_effort")
+        if reasoning is not None:
+            kwargs['reasoning'] = {"effort": reasoning}
+
         stream_response = await app.openrouter_client.chat.send_async(**kwargs)
 
         # OpenAI format streams tool calls in parts