From 1e76a8f8e68f71a4ea833446ea9d4b0f07b27302 Mon Sep 17 00:00:00 2001
From: qin-ctx <qinhaojie.exe@bytedance.com>
Date: Wed, 8 Apr 2026 14:41:18 +0800
Subject: [PATCH] fix(openclaw): sanitize and cap recall queries

Recall should use cleaned user text and avoid sending oversized prompts
to retrieval. Add unit coverage for sanitization and truncation behavior.
---
 examples/openclaw-plugin/index.ts             | 48 ++++++++++++++++++-
 .../tests/ut/index-utils.test.ts              | 27 +++++++++++
 2 files changed, 73 insertions(+), 2 deletions(-)

diff --git a/examples/openclaw-plugin/index.ts b/examples/openclaw-plugin/index.ts
index 2bf71daf2..849501402 100644
--- a/examples/openclaw-plugin/index.ts
+++ b/examples/openclaw-plugin/index.ts
@@ -11,6 +11,7 @@ import {
   compileSessionPatterns,
   isTranscriptLikeIngest,
   extractLatestUserText,
+  sanitizeUserTextForCapture,
   shouldBypassSession,
 } from "./text-utils.js";
 import {
@@ -110,6 +111,7 @@ type OpenClawPluginApi = {
 const MAX_OPENVIKING_STDERR_LINES = 200;
 const MAX_OPENVIKING_STDERR_CHARS = 256_000;
 const AUTO_RECALL_TIMEOUT_MS = 5_000;
+const RECALL_QUERY_MAX_CHARS = 4_000;
 
 /**
  * OpenViking `UserIdentifier` allows only [a-zA-Z0-9_-] for agent_id
@@ -128,6 +130,39 @@ export function sanitizeOpenVikingAgentIdHeader(raw: string): string {
   return normalized.length > 0 ? normalized : "ov_agent";
 }
 
+export type PreparedRecallQuery = {
+  query: string;
+  truncated: boolean;
+  originalChars: number;
+  finalChars: number;
+};
+
+export function prepareRecallQuery(rawText: string): PreparedRecallQuery {
+  const sanitized = sanitizeUserTextForCapture(rawText).trim();
+  const originalChars = sanitized.length;
+
+  if (!sanitized) {
+    return {
+      query: "",
+      truncated: false,
+      originalChars: 0,
+      finalChars: 0,
+    };
+  }
+
+  const query =
+    sanitized.length > RECALL_QUERY_MAX_CHARS
+      ? sanitized.slice(0, RECALL_QUERY_MAX_CHARS).trim()
+      : sanitized;
+
+  return {
+    query,
+    truncated: sanitized.length > RECALL_QUERY_MAX_CHARS,
+    originalChars,
+    finalChars: query.length,
+  };
+}
+
 function extractAgentIdFromSessionKey(sessionKey?: string): string | undefined {
   const raw = typeof sessionKey === "string" ? sessionKey.trim() : "";
   if (!raw) {
@@ -882,12 +917,21 @@ const contextEnginePlugin = {
       }
 
       const eventObj = (event ?? {}) as { messages?: unknown[]; prompt?: string };
-      const queryText =
-        extractLatestUserText(eventObj.messages) ||
+      const latestUserText = extractLatestUserText(eventObj.messages);
+      const rawRecallQuery =
+        latestUserText ||
         (typeof eventObj.prompt === "string" ? eventObj.prompt.trim() : "");
+      const recallQuery = prepareRecallQuery(rawRecallQuery);
+      const queryText = recallQuery.query;
       if (!queryText) {
         return;
       }
+      if (recallQuery.truncated) {
+        verboseRoutingInfo(
+          `openviking: recall query truncated (` +
+            `chars=${recallQuery.originalChars}->${recallQuery.finalChars})`,
+        );
+      }
 
       const prependContextParts: string[] = [];
 
diff --git a/examples/openclaw-plugin/tests/ut/index-utils.test.ts b/examples/openclaw-plugin/tests/ut/index-utils.test.ts
index 77022ffd1..c8b91844b 100644
--- a/examples/openclaw-plugin/tests/ut/index-utils.test.ts
+++ b/examples/openclaw-plugin/tests/ut/index-utils.test.ts
@@ -1,6 +1,7 @@
 import { describe, expect, it } from "vitest";
 
 import {
+  prepareRecallQuery,
   sanitizeOpenVikingAgentIdHeader,
   createSessionAgentResolver,
 } from "../../index.js";
@@ -97,3 +98,29 @@ describe("createSessionAgentResolver", () => {
     expect(r1.resolved).toBe(r2.resolved);
   });
 });
+
+describe("prepareRecallQuery", () => {
+  it("sanitizes the recall query before returning it", () => {
+    const result = prepareRecallQuery(
+      "  <relevant-memories>stale</relevant-memories>\nhello   world\u0000  ",
+    );
+
+    expect(result).toEqual({
+      query: "hello world",
+      truncated: false,
+      originalChars: 11,
+      finalChars: 11,
+    });
+  });
+
+  it("truncates overly long recall queries after sanitization", () => {
+    const rawQuery = "x".repeat(4100);
+
+    const result = prepareRecallQuery(rawQuery);
+
+    expect(result.query).toBe("x".repeat(4000));
+    expect(result.truncated).toBe(true);
+    expect(result.originalChars).toBe(4100);
+    expect(result.finalChars).toBe(4000);
+  });
+});