Support finish reason in legacy pipelines

Author: Michal Kulakowski

src/llm/apis/openai_completions.cpp

@@ -416,7 +416,7 @@ std::string OpenAIChatCompletionsHandler::serializeUnaryResponse(ov::genai::Enco
         ParsedOutput parsedOutput = parseOutputIfNeeded(tokens);
         jsonResponse.StartObject();
         // finish_reason: "stop" in regular scenario, "tool_calls" if output contains tool calls
-        auto finishReason = mapFinishReason(ov::genai::GenerationFinishReason::STOP, !parsedOutput.toolCalls.empty());
+        auto finishReason = mapFinishReason(results.finish_reasons[index], !parsedOutput.toolCalls.empty());
         jsonResponse.FinishReason(finishReason.value_or("unknown"));
         // index: integer; Choice index, only n=1 supported anyway
         jsonResponse.Index(index++);
@@ -482,7 +482,7 @@ std::string OpenAIChatCompletionsHandler::serializeUnaryResponse(ov::genai::VLMD
         ParsedOutput parsedOutput = parseOutputIfNeeded(generatedTokens);
         jsonResponse.StartObject();
         // finish_reason: "stop" in regular scenario, "tool_calls" if output contains tool calls
-        auto finishReason = mapFinishReason(ov::genai::GenerationFinishReason::STOP, !parsedOutput.toolCalls.empty());
+        auto finishReason = mapFinishReason(results.finish_reasons[index], !parsedOutput.toolCalls.empty());
         jsonResponse.FinishReason(finishReason.value_or("unknown"));
         // index: integer; Choice index, only n=1 supported anyway
         jsonResponse.Index(index++);

src/llm/language_model/legacy/servable.cpp

@@ -228,7 +228,11 @@ absl::Status LegacyServable::preparePartialResponse(std::shared_ptr<GenAiServabl
         if (!executionContext->lastStreamerCallbackOutput.empty()) {
             lastTextChunk = lastTextChunk + executionContext->lastStreamerCallbackOutput;
         }
-        std::string serializedChunk = executionContext->apiHandler->serializeStreamingChunk(lastTextChunk, ov::genai::GenerationFinishReason::STOP);
+        ov::genai::GenerationFinishReason finishReason = ov::genai::GenerationFinishReason::STOP;
+        if (!legacyExecutionContext->results.finish_reasons.empty()) {
+            finishReason = legacyExecutionContext->results.finish_reasons[0];
+        }
+        std::string serializedChunk = executionContext->apiHandler->serializeStreamingChunk(lastTextChunk, finishReason);
         if (!serializedChunk.empty()) {
             executionContext->response = wrapTextInServerSideEventMessage(serializedChunk);
         }

src/test/llm/llmnode_test.cpp

@@ -2606,7 +2606,7 @@ INSTANTIATE_TEST_SUITE_P(
     ::testing::Values(
         // params:     model name, generate expected output, check logprobs, check finish reason, test speculative decoding, supports empty handshake msg
         TestParameters{"lm_cb_regular", true, true, true, false, true},
-        TestParameters{"lm_legacy_regular", false, false, false, false, false},
+        TestParameters{"lm_legacy_regular", false, false, true, false, false},
         TestParameters{"vlm_cb_regular", false, true, true, false, true},
         TestParameters{"vlm_legacy_regular", false, false, false, false, false}));