fix(proxy): improve URL building and remove redundant model mapping

- Add model parameter to request logs for better debugging
- Fix duplicate /v1/v1 in URL when both base_url and endpoint have version
- Extend ?beta=true parameter to /v1/chat/completions endpoint
- Remove model mapping from transform layer (now handled by model_mapper)
- Add DeepSeek max_tokens clamping (1-8192 range)

src-tauri/src/proxy/forwarder.rs

@@ -666,7 +666,11 @@ impl RequestForwarder {
 
         // 输出请求信息日志
         let tag = adapter.name();
-        log::info!("[{tag}] >>> 请求 URL: {url}");
+        let request_model = filtered_body
+            .get("model")
+            .and_then(|v| v.as_str())
+            .unwrap_or("<none>");
+        log::info!("[{tag}] >>> 请求 URL: {url} (model={request_model})");
         if let Ok(body_str) = serde_json::to_string(&filtered_body) {
             log::debug!(
                 "[{tag}] >>> 请求体内容 ({}字节): {}",