fix(semantic-consistency): keep a usable reason when the model omits one

SemanticConsistencyNode#buildValidationResult passed the model's reason
straight into SqlRetryDto.semantic(). A response of {"passed":false}
without a "reason" field therefore stored a null reason, which then
reaches SqlGenerationDTO.exceptionMessage and is rendered into the
{error_message} section of the sql-error-fixer prompt — leaving the
repair model with an empty "错误信息" block and nothing to act on.

Fall back to a generic notice when the reason is blank so the retry
prompt always carries an explanation. Behaviour is unchanged whenever
the model supplies a reason.

Add a regression test asserting the stored reason is never null while
the failure verdict and retry routing are preserved.

Author: ydflow

data-agent-management/src/main/java/com/alibaba/cloud/ai/dataagent/workflow/node/SemanticConsistencyNode.java

@@ -29,6 +29,7 @@
 import com.alibaba.cloud.ai.graph.streaming.StreamingOutput;
 import lombok.AllArgsConstructor;
 import lombok.extern.slf4j.Slf4j;
+import org.apache.commons.lang3.StringUtils;
 import org.springframework.ai.chat.model.ChatResponse;
 import org.springframework.ai.converter.BeanOutputConverter;
 import org.springframework.stereotype.Component;
@@ -109,14 +110,20 @@ private Map<String, Object> buildStructuralValidationFailure(OverAllState state,
 
 	/**
 	 * Build validation result
+	 *
+	 * <p>
+	 * The reason is rendered into the {@code sql-error-fixer} prompt on the retry path, so a
+	 * null reason would leave the model with an empty "错误信息" section. Fall back to a
+	 * generic notice when the model reports a failure without explaining it.
 	 */
 	private Map<String, Object> buildValidationResult(boolean passed, String validationResult) {
 		if (passed) {
 			return Map.of(SEMANTIC_CONSISTENCY_NODE_OUTPUT, true);
 		}
 		else {
 			return Map.of(SEMANTIC_CONSISTENCY_NODE_OUTPUT, false, SQL_REGENERATE_REASON,
-					SqlRetryDto.semantic(validationResult));
+					SqlRetryDto.semantic(StringUtils.isNotBlank(validationResult) ? validationResult
+							: "语义一致性校验未通过，模型未给出具体原因"));
 		}
 	}
 

data-agent-management/src/test/java/com/alibaba/cloud/ai/dataagent/workflow/node/SemanticConsistencyNodeTest.java

@@ -125,6 +125,24 @@ void apply_invalidSql_returnsGeneratorWithFailOutput() throws Exception {
 		assertEquals(new SqlRetryDto("表不存在", true, false), retry);
 	}
 
+	@Test
+	void apply_failedWithoutReason_doesNotStoreNullReason() throws Exception {
+		OverAllState state = createTestState();
+		setupBasicState(state, "SELECT * FROM nonexistent");
+
+		// LLM may omit "reason" entirely when it only reports the verdict
+		when(nl2SqlService.performSemanticConsistency(any(SemanticConsistencyDTO.class)))
+			.thenReturn(Flux.just(ChatResponseUtil.createPureResponse("{\"passed\":false}")));
+
+		NodeExecution execution = execute(semanticConsistencyNode.apply(state), SEMANTIC_CONSISTENCY_NODE_OUTPUT);
+
+		assertEquals(false, execution.finalResult().get(SEMANTIC_CONSISTENCY_NODE_OUTPUT));
+		SqlRetryDto retry = (SqlRetryDto) execution.finalResult().get(SQL_REGENERATE_REASON);
+		assertNotNull(retry, "retry reason must still be produced so the workflow loops back");
+		assertTrue(retry.semanticFail());
+		assertNotNull(retry.reason(), "reason must not be null; it is rendered into the repair prompt");
+	}
+
 	@Test
 	void apply_missingEvidence_throwsException() {
 		OverAllState state = createTestState();