fix(matrix): truncate thread starter body on code-point boundaries

ly-wang19 · Bartok9 · commit 15beecb66b6a · 2026-06-26T19:14:03.000-04:00
Matrix thread-starter previews truncated long bodies by raw UTF-16 slice, which could cut an astral character (e.g. emoji) and leave a lone surrogate, rendering mojibake in the agent's thread context. Reuse the existing sliceUtf16Safe helper so the cut backs up to a valid surrogate boundary, preserving the 500-code-unit limit and '...' suffix. Adds a regression test that fails against the raw-slice implementation. Salvages the original fix from #96407 (auto-closed by the active-PR queue cap). Preserves @ly-wang19's authorship; rebased clean onto main by @Bartok9.
diff --git a/extensions/matrix/src/matrix/monitor/thread-context.test.ts b/extensions/matrix/src/matrix/monitor/thread-context.test.ts
@@ -23,6 +23,23 @@ describe("matrix thread context", () => {
     ).toBe("Thread starter body");
   });
 
+  it("truncates long thread starter bodies on code-point boundaries", () => {
+    const summary = summarizeMatrixThreadStarterEvent({
+      event_id: "$root",
+      sender: "@alice:example.org",
+      type: "m.room.message",
+      origin_server_ts: Date.now(),
+      content: {
+        msgtype: "m.text",
+        // 496 "a" + astral emoji (surrogate pair at units 496-497) + tail.
+        // A raw slice(0, 497) would cut the pair and leave a lone high surrogate.
+        body: `${"a".repeat(496)}\u{1F600}bcd`,
+      },
+    } as MatrixRawEvent);
+    expect(summary).toBe(`${"a".repeat(496)}...`);
+    expect(summary && /[\uD800-\uDFFF]/.test(summary)).toBe(false);
+  });
+
   it("marks media-only thread starter events instead of returning bare filenames", () => {
     expect(
       summarizeMatrixThreadStarterEvent({
diff --git a/extensions/matrix/src/matrix/monitor/thread-context.ts b/extensions/matrix/src/matrix/monitor/thread-context.ts
@@ -1,4 +1,5 @@
 // Matrix plugin module implements thread context behavior.
+import { sliceUtf16Safe } from "openclaw/plugin-sdk/text-utility-runtime";
 import type { MatrixClient } from "../sdk.js";
 import { summarizeMatrixMessageContextEvent, trimMatrixMaybeString } from "./context-summary.js";
 import type { MatrixRawEvent } from "./types.js";
@@ -17,7 +18,7 @@ function truncateThreadStarterBody(value: string): string {
   if (value.length <= MAX_THREAD_STARTER_BODY_LENGTH) {
     return value;
   }
-  return `${value.slice(0, MAX_THREAD_STARTER_BODY_LENGTH - 3)}...`;
+  return `${sliceUtf16Safe(value, 0, MAX_THREAD_STARTER_BODY_LENGTH - 3)}...`;
 }
 
 export function summarizeMatrixThreadStarterEvent(event: MatrixRawEvent): string | undefined {

Original file line number	Diff line number	Diff line change
`@@ -1,4 +1,5 @@`
`1`	`1`	`// Matrix plugin module implements thread context behavior.`
	`2`	`+import { sliceUtf16Safe } from "openclaw/plugin-sdk/text-utility-runtime";`
`2`	`3`	`import type { MatrixClient } from "../sdk.js";`
`3`	`4`	`import { summarizeMatrixMessageContextEvent, trimMatrixMaybeString } from "./context-summary.js";`
`4`	`5`	`import type { MatrixRawEvent } from "./types.js";`
`@@ -17,7 +18,7 @@ function truncateThreadStarterBody(value: string): string {`
`17`	`18`	`if (value.length <= MAX_THREAD_STARTER_BODY_LENGTH) {`
`18`	`19`	`return value;`
`19`	`20`	`}`
`20`		- return `${value.slice(0, MAX_THREAD_STARTER_BODY_LENGTH - 3)}...`;
	`21`	+ return `${sliceUtf16Safe(value, 0, MAX_THREAD_STARTER_BODY_LENGTH - 3)}...`;
`21`	`22`	`}`
`22`	`23`
`23`	`24`	`export function summarizeMatrixThreadStarterEvent(event: MatrixRawEvent): string \| undefined {`