fix: preserve empty reasoning_content for DeepSeek V4 thinking mode (#24146)

Co-authored-by: Simon Klee <hello@simonklee.dk>

packages/opencode/src/provider/transform.ts

@@ -185,8 +185,9 @@ function normalizeMessages(
         // Filter out reasoning parts from content
         const filteredContent = msg.content.filter((part: any) => part.type !== "reasoning")
 
-        // Include reasoning_content | reasoning_details directly on the message for all assistant messages
+        // Include reasoning_content | reasoning_details directly on the message for all assistant messages.
-        if (reasoningText) {
+        // Always set the field even when empty — some providers (e.g. DeepSeek) may return empty
+        // reasoning_content which still needs to be sent back in subsequent requests.
         return {
           ...msg,
           content: filteredContent,
@@ -200,12 +201,6 @@ function normalizeMessages(
         }
       }
 
-        return {
-          ...msg,
-          content: filteredContent,
-        }
-      }
-
       return msg
     })
   }