fix(gateway): avoid low OpenAI-compatible test token cap

apps/aether-gateway/src/handlers/public/support/test_connection/route.rs

@@ -169,7 +169,11 @@ pub(super) async fn maybe_build_local_test_connection_route_response(
     }
 
     let mut provider_request_body = match format_value.as_str() {
-        "openai:chat" | "claude:messages" => json!({
+        "openai:chat" => json!({
+            "model": model,
+            "messages": [{"role": "user", "content": "Health check"}],
+        }),
+        "claude:messages" => json!({
             "model": model,
             "messages": [{"role": "user", "content": "Health check"}],
             "max_tokens": 5,

apps/aether-gateway/src/tests/frontdoor/public_support.rs

@@ -1920,6 +1920,10 @@ async fn gateway_handles_public_test_connection_without_hitting_fallback_probe()
                 );
                 assert_eq!(body_json["model"], "gpt-5");
                 assert_eq!(body_json["messages"][0]["content"], "Health check");
+                assert!(
+                    body_json.get("max_tokens").is_none(),
+                    "public OpenAI-compatible test connection must not force a tiny max_tokens value"
+                );
                 Json(json!({"id": "resp_local_test"})).into_response()
             }
         }),