fix(agents): keep tool-result truncation UTF-16 safe (#102087)

chengzhichao-xydt · claude · steipete · web-flow · commit 9e75ce9dd1e1 · 2026-07-09T04:49:24.000+01:00
* fix(agents): keep tool-result truncation UTF-16 safe

Replace raw .slice() calls in tool-result truncation with UTF-16-safe
helpers (sliceUtf16Safe/truncateUtf16Safe) so surrogate pairs are not
split when capping tool output, error-tail detection, or aggregate
elision markers.

- hasImportantTail: sliceUtf16Safe(text, -2000)
- appendBoundedTruncationSuffix: truncateUtf16Safe + sliceUtf16Safe
- truncateToolResultText head/tail/default paths: sliceUtf16Safe
- formatAggregateElisionText fallback: truncateUtf16Safe

Added regression tests for emoji at char and head+tail boundaries.

Co-Authored-By: Claude Opus 4.8 &lt;noreply@anthropic.com&gt;

* test(agents): cover exact tool-result UTF-16 cuts

---------

Co-authored-by: chengzhichao-xydt &lt;chengzhichao-xydt@users.noreply.github.com&gt;
Co-authored-by: Claude Opus 4.8 &lt;noreply@anthropic.com&gt;
Co-authored-by: Peter Steinberger &lt;steipete@gmail.com&gt;
diff --git a/src/agents/embedded-agent-runner/tool-result-truncation.test.ts b/src/agents/embedded-agent-runner/tool-result-truncation.test.ts
@@ -166,6 +166,32 @@ describe("truncateToolResultText", () => {
     expect(result).toContain("[custom-truncated]");
     expect(result.length).toBeGreaterThan(250);
   });
+
+  it("keeps direct and suffix-only cuts on complete code points", () => {
+    expect(
+      truncateToolResultText("aaa😀z", 5, {
+        suffix: "!",
+        minKeepChars: 0,
+      }),
+    ).toBe("aaa!");
+    expect(
+      truncateToolResultText("abcdef", 1, {
+        suffix: "😀",
+        minKeepChars: 0,
+      }),
+    ).toBe("");
+  });
+
+  it("keeps both head and tail cuts on complete code points", () => {
+    const marker = "\n\n⚠️ [... middle content omitted — showing head and tail ...]\n\n";
+    const text = `${"a".repeat(6)}😀${"m".repeat(100)}😀${"x".repeat(22)} Error`;
+    expect(
+      truncateToolResultText(text, 100, {
+        suffix: "!",
+        minKeepChars: 1,
+      }),
+    ).toBe(`${"a".repeat(6)}${marker}${"x".repeat(22)} Error!`);
+  });
 });
 
 describe("getToolResultTextLength", () => {
diff --git a/src/agents/embedded-agent-runner/tool-result-truncation.ts b/src/agents/embedded-agent-runner/tool-result-truncation.ts
@@ -3,6 +3,7 @@
  */
 import { existsSync } from "node:fs";
 import { normalizeLowercaseStringOrEmpty } from "@openclaw/normalization-core/string-coerce";
+import { sliceUtf16Safe, truncateUtf16Safe } from "@openclaw/normalization-core/utf16-slice";
 import type { OpenClawConfig } from "../../config/types.openclaw.js";
 import { formatErrorMessage } from "../../infra/errors.js";
 import type { TextContent } from "../../llm/types.js";
@@ -139,11 +140,12 @@ function appendBoundedTruncationSuffix(params: {
       return finalText;
     }
     if (keptText.length === 0) {
-      return finalText.slice(0, params.maxChars);
+      return truncateUtf16Safe(finalText, params.maxChars);
     }
     const overflow = finalText.length - params.maxChars;
-    const nextKeptText = keptText.slice(0, Math.max(0, keptText.length - overflow));
-    keptText = nextKeptText.length < keptText.length ? nextKeptText : keptText.slice(0, -1);
+    const nextKeptText = sliceUtf16Safe(keptText, 0, Math.max(0, keptText.length - overflow));
+    keptText =
+      nextKeptText.length < keptText.length ? nextKeptText : sliceUtf16Safe(keptText, 0, -1);
   }
 }
 
@@ -158,8 +160,8 @@ const MIDDLE_OMISSION_MARKER =
  * which should be preserved during truncation.
  */
 function hasImportantTail(text: string): boolean {
-  // Check last ~2000 chars for error-like patterns
-  const tail = normalizeLowercaseStringOrEmpty(text.slice(-2000));
+  // Check last ~2000 chars for error-like patterns without splitting a surrogate pair.
+  const tail = normalizeLowercaseStringOrEmpty(sliceUtf16Safe(text, -2000));
   return (
     /\b(error|exception|failed|fatal|traceback|panic|stack trace|errno|exit code)\b/.test(tail) ||
     // JSON closing — if the output is JSON, the tail has closing structure
@@ -213,7 +215,8 @@ export function truncateToolResultText(
         tailStart = tailNewline + 1;
       }
 
-      const keptText = text.slice(0, headCut) + MIDDLE_OMISSION_MARKER + text.slice(tailStart);
+      const keptText =
+        sliceUtf16Safe(text, 0, headCut) + MIDDLE_OMISSION_MARKER + sliceUtf16Safe(text, tailStart);
       return appendBoundedTruncationSuffix({
         keptText,
         originalTextLength: text.length,
@@ -229,7 +232,7 @@ export function truncateToolResultText(
   if (lastNewline > budget * 0.8) {
     cutPoint = lastNewline;
   }
-  const keptText = text.slice(0, cutPoint);
+  const keptText = sliceUtf16Safe(text, 0, cutPoint);
   return appendBoundedTruncationSuffix({
     keptText,
     originalTextLength: text.length,
