fix: GH-4089 Adjusted the default priority of SafeGuardAdvisor to ensure it is always higher than that of MessageChatMemoryAdvisor, preventing sensitive terms in chat memory from repeatedly triggering SafeGuardAdvisor's interception mechanism.

Signed-off-by: Sun Yuhan <[email protected]>

Author: sunyuhan1998

spring-ai-client-chat/src/main/java/org/springframework/ai/chat/client/advisor/SafeGuardAdvisor.java

@@ -23,6 +23,7 @@
 
 import org.springframework.ai.chat.client.ChatClientRequest;
 import org.springframework.ai.chat.client.ChatClientResponse;
+import org.springframework.ai.chat.client.advisor.api.Advisor;
 import org.springframework.ai.chat.client.advisor.api.CallAdvisor;
 import org.springframework.ai.chat.client.advisor.api.CallAdvisorChain;
 import org.springframework.ai.chat.client.advisor.api.StreamAdvisor;
@@ -46,7 +47,12 @@ public class SafeGuardAdvisor implements CallAdvisor, StreamAdvisor {
 
 	private static final String DEFAULT_FAILURE_RESPONSE = "I'm unable to respond to that due to sensitive content. Could we rephrase or discuss something else?";
 
-	private static final int DEFAULT_ORDER = 0;
+	/**
+	 * The default priority of {@code SafeGuardAdvisor} should always be higher than that
+	 * of {@code MessageChatMemoryAdvisor} to prevent sensitive words in chat memory from
+	 * repeatedly triggering {@code SafeGuardAdvisor}'s interception mechanism.
+	 */
+	private static final int DEFAULT_ORDER = Advisor.DEFAULT_CHAT_MEMORY_PRECEDENCE_ORDER - 1;
 
 	private final String failureResponse;
 

spring-ai-docs/src/main/antora/modules/ROOT/pages/api/advisors.adoc

@@ -385,7 +385,11 @@ Based on the article: [Re-Reading Improves Reasoning in LLMs](https://arxiv.org/
 * `SafeGuardAdvisor`
 +
 A simple advisor designed to prevent the model from generating harmful or inappropriate content.
-
++
+[NOTE]
+====
+If you have both `SafeGuardAdvisor` and `MessageChatMemoryAdvisor` enabled and have manually set their `order`, make sure that `SafeGuardAdvisor` has a higher priority than `MessageChatMemoryAdvisor` to prevent sensitive words in chat memory from repeatedly triggering `SafeGuardAdvisor`'s interception mechanism.
+====
 
 === Streaming vs Non-Streaming