Fixed endless generations in test_callback_one_string test (#1189)

See
https://productionresultssa7.blob.core.windows.net/actions-results/1d9c7ed7-f60f-463a-8dba-2898f6f39e0a/workflow-job-run-2ad6080a-b02b-5d2d-feb5-675d9367578e/logs/job/job-logs.txt?rsct=text%2Fplain&se=2024-11-11T12%3A35%3A03Z&sig=cE1uxQm2H0TswczNt4jESUwM1%2BzN2uQBHxsm7Tqw0AI%3D&ske=2024-11-11T22%3A38%3A18Z&skoid=ca7593d4-ee42-46cd-af88-8b886a2f84eb&sks=b&skt=2024-11-11T10%3A38%3A18Z&sktid=398a6654-997b-47e9-b12b-9515b896b4de&skv=2024-08-04&sp=r&spr=https&sr=b&st=2024-11-11T12%3A24%3A58Z&sv=2024-08-04

A lot of words are printed as max_new_tokens is quite huge number, while
exception is expected as streamer cannot work with batch.

To fix hanging of tests in this PR
openvinotoolkit/openvino.genai#882

src/continuous_batching_impl.cpp

@@ -262,6 +262,9 @@ ContinuousBatchingPipeline::ContinuousBatchingImpl::generate(const std::vector<o
         }
     }, streamer);
 
+    OPENVINO_ASSERT(streamer_ptr == nullptr || input_ids.size() == 1 && (sampling_params[0].is_greedy_decoding() || sampling_params[0].is_multinomial()),
+        "Currently streaming is possible only with batch size=1 and only for greedy or multinomial decoding");
+
     std::vector<GenerationHandle> generations;
     for (size_t request_id = 0; request_id < input_ids.size(); ++request_id) {
         OPENVINO_ASSERT(1 == input_ids[request_id].get_shape().at(0), "Use multiple tensors to pass a batch.");
@@ -283,7 +286,7 @@ ContinuousBatchingPipeline::ContinuousBatchingImpl::generate(const std::vector<o
         m_requests.clear();
     };
 
-    bool continue_generation = true, step_throws_exception = false;
+    bool continue_generation = true;
     while (has_non_finished_requests() && continue_generation) {
         try {
             step();