Fix failing integration tests (#1332)

<!--
Thank you for opening a pull request!

Please add a brief description of the proposed change here.
Also, please tick the appropriate points in the checklist below.
-->

## Motivation and Context
<!-- Why is this change needed? What problem does it solve? -->

- Skip Google LLMProvider because of a
[bug](googleapis/python-genai#1723);
- Adjust rollback test expectations after a
[fix](#1308);
- Update a QWEN profile used in OpenRouterModels to less flaky.

## Breaking Changes
<!-- Will users need to update their code or configurations? -->

---

#### Type of the changes
- [ ] New feature (non-breaking change which adds functionality)
- [ ] Bug fix (non-breaking change which fixes an issue)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [x] Tests improvement
- [ ] Refactoring

#### Checklist
- [x] The pull request has a description of the proposed change
- [x] I read the [Contributing
Guidelines](https://github.com/JetBrains/koog/blob/main/CONTRIBUTING.md)
before opening the pull request
- [x] The pull request uses **`develop`** as the base branch
- [x] Tests for the changes have been added
- [x] All new and existing tests passed

##### Additional steps for pull requests adding a new feature
- [ ] An issue describing the proposed change exists
- [ ] The pull request includes a link to the issue
- [ ] The change was discussed and approved in the issue
- [ ] Docs have been added / updated

Author: aozherelyeva

integration-tests/src/jvmTest/kotlin/ai/koog/integration/tests/agent/AIAgentIntegrationTest.kt

@@ -749,7 +749,13 @@ class AIAgentIntegrationTest : AIAgentTestBase() {
             shouldContain(saySaveLog.trim())
             shouldContain(sayByeLog.trim())
             shouldContain(rollbackPerformingLog.trim())
-            saySaveLog.trim().toRegex().findAll(this).count() shouldBe 2
+            // After #1308: checkpoint restoration doesn't re-execute the checkpointed node
+            // nodeHello and nodeSave are executed once (no re-execution after rollback)
+            sayHelloLog.trim().toRegex().findAll(this).count() shouldBe 1
+            saySaveLog.trim().toRegex().findAll(this).count() shouldBe 1
+            // one rollback should be performed and tracked
+            rollbackPerformingLog.trim().toRegex().findAll(this).count() shouldBe 1
+            // nodeBye is executed twice (once before rollback, once after rollback)
             sayByeLog.trim().toRegex().findAll(this).count() shouldBe 2
         }
     }

integration-tests/src/jvmTest/kotlin/ai/koog/integration/tests/capabilities/ModelCapabilitiesIntegrationTest.kt

@@ -236,6 +236,10 @@ class ModelCapabilitiesIntegrationTest {
                 }
 
                 LLMCapability.MultipleChoices -> {
+                    assumeTrue(
+                        model.provider !is LLMProvider.Google,
+                        "https://github.com/googleapis/python-genai/issues/1723"
+                    )
                     val prompt = prompt(
                         "cap-multiple-choices-positive",
                         params = LLMParams(numberOfChoices = 2)

integration-tests/src/jvmTest/kotlin/ai/koog/integration/tests/utils/Models.kt

@@ -44,7 +44,7 @@ object Models {
     @JvmStatic
     fun openRouterModels(): Stream<LLModel> = Stream.of(
         OpenRouterModels.DeepSeekV30324,
-        OpenRouterModels.Qwen3VL,
+        OpenRouterModels.Qwen2_5,
     )
 
     @JvmStatic