Refactor safety response handling in guardrails.mdx (#1452)

## Overview
When the judge LLM returns “UNSAFE”, the agent enters an infinite loop.

## Type of change

**Type:** Update existing documentation / bug

## Related issues/PRs
<!--
Link to related issues, feature PRs, or discussions (if applicable)

To automatically close an issue when this PR is merged, use closing
keywords:
- "closes #123" or "fixes #123" or "resolves #123"

For regular references without auto-closing, just use:
- "#123" or "See issue #123"

Examples:
- closes #456 (will auto-close issue #456 when PR is merged)
- See #789 for context (will reference but not auto-close issue #789)
-->
- GitHub issue: closes #1435
- Feature PR:

<!-- For LangChain employees, if applicable: -->
- Linear issue:
- Slack thread:

## Checklist
<!-- Put an 'x' in all boxes that apply -->
- [x] I have read the [contributing guidelines](README.md)
- [x] I have tested my changes locally using `docs dev`
- [x] All code examples have been tested and work correctly
- [x] I have used **root relative** paths for internal links
- [x] I have updated navigation in `src/docs.json` if needed

(Internal team members only / optional): Create a preview deployment as
necessary using the [Create Preview Branch
workflow](https://github.com/langchain-ai/docs/actions/workflows/create-preview-branch.yml)

## Additional notes
<!-- Any other information that would be helpful for reviewers -->

---------

Co-authored-by: Lauren Hirata Singh <[email protected]>

Author: mcavdar

src/oss/langchain/guardrails.mdx

@@ -484,13 +484,7 @@ class SafetyGuardrailMiddleware(AgentMiddleware):
         result = self.safety_model.invoke([{"role": "user", "content": safety_prompt}])
 
         if "UNSAFE" in result.content:
-            return {
-                "messages": [{
-                    "role": "assistant",
-                    "content": "I cannot provide that response. Please rephrase your request."
-                }],
-                "jump_to": "end"
-            }
+            last_message.content = "I cannot provide that response. Please rephrase your request."
 
         return None
 
@@ -537,13 +531,7 @@ def safety_guardrail(state: AgentState, runtime: Runtime) -> dict[str, Any] | No
     result = safety_model.invoke([{"role": "user", "content": safety_prompt}])
 
     if "UNSAFE" in result.content:
-        return {
-            "messages": [{
-                "role": "assistant",
-                "content": "I cannot provide that response. Please rephrase your request."
-            }],
-            "jump_to": "end"
-        }
+        last_message.content = "I cannot provide that response. Please rephrase your request."
 
     return None