fix(e2e): keep phase log tails UTF-8 safe (#109923)

wangmiao0668000666 · claude · steipete · web-flow · commit 998f0ed27d81 · 2026-07-20T19:45:35.000-07:00
* fix(e2e): keep phase log tails UTF-8 safe The phase runner keeps a bounded in-memory log tail per phase and writes it to stderr when a phase fails. The byte-based cut can land inside a multi-byte UTF-8 character, and decoding from that offset emits U+FFFD replacement characters at the start of the diagnostics tail. Reuse the decodeUtf8Tail helper from scripts/e2e/lib/text-file-utils.mjs (#109669) so the retained window starts on a character boundary. Co-Authored-By: Claude <noreply@anthropic.com> * fix(e2e): declare decodeUtf8Tail in text-file-utils types phase-runner.ts imports decodeUtf8Tail from text-file-utils.mjs; the adjacent declaration file must export it or check-test-types fails with TS2305. Co-Authored-By: Claude <noreply@anthropic.com> * refactor(e2e): reuse tailText wrapper for phase log tails Co-Authored-By: Claude <noreply@anthropic.com> * test(e2e): focus phase tail regression Co-authored-by: wangmiao0668000666 <wang.miao86@xydigit.com> --------- Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Peter Steinberger <steipete@gmail.com>
diff --git a/scripts/e2e/parallels/phase-runner.ts b/scripts/e2e/parallels/phase-runner.ts
@@ -3,6 +3,7 @@ import { appendFileSync } from "node:fs";
 import { writeFile } from "node:fs/promises";
 import path from "node:path";
 import { clampTimerTimeoutMs } from "@openclaw/normalization-core/number-coercion";
+import { tailText } from "../lib/text-file-utils.mjs";
 import { say, warn } from "./host-command.ts";
 
 const PHASE_LOG_TAIL_MAX_BYTES = 512 * 1024;
@@ -15,8 +16,8 @@ function appendTextTail(current: string, chunk: string, maxBytes: number): strin
   }
   const marker = `[phase log tail truncated to last ${maxBytes} bytes]\n`;
   const tailBytes = Math.max(0, maxBytes - Buffer.byteLength(marker));
-  const tail = Buffer.from(combined).subarray(-tailBytes).toString("utf8");
-  return `${marker}${tail}`;
+  // tailText owns the UTF-8-safe byte truncation; the marker keeps the tail self-describing.
+  return `${marker}${tailText(combined, tailBytes)}`;
 }
 
 function resolvePhaseTimeoutMs(timeoutSeconds: number): number {
diff --git a/test/scripts/parallels-phase-runner.test.ts b/test/scripts/parallels-phase-runner.test.ts
@@ -0,0 +1,43 @@
+// Parallels Phase Runner tests cover bounded in-memory phase log tails.
+import { afterEach, expect, it, vi } from "vitest";
+import { PhaseRunner } from "../../scripts/e2e/parallels/phase-runner.ts";
+import { cleanupTempDirs, makeTempDir } from "../helpers/temp-dir.js";
+
+const tempRoots: string[] = [];
+
+function makeTempRoot() {
+  return makeTempDir(tempRoots, "openclaw-parallels-phase-runner-");
+}
+
+afterEach(() => {
+  cleanupTempDirs(tempRoots);
+  vi.restoreAllMocks();
+});
+
+async function captureFailedPhaseTail(runner: PhaseRunner, text: string): Promise<string> {
+  const written: string[] = [];
+  vi.spyOn(process.stderr, "write").mockImplementation((chunk) => {
+    written.push(String(chunk));
+    return true;
+  });
+  await expect(
+    runner.phase("utf8-tail", 60, () => {
+      runner.append(text);
+      throw new Error("boom");
+    }),
+  ).rejects.toThrow("boom");
+  return written.join("");
+}
+
+it("keeps the truncated phase tail UTF-8 safe when the byte cut splits a character", async () => {
+  // 134 bytes total; the retained window starts one byte into the 4-byte
+  // emoji, so a byte-naive decode would emit replacement characters.
+  const tail = await captureFailedPhaseTail(
+    new PhaseRunner(makeTempRoot(), 128),
+    `${"x".repeat(50)}😀${"y".repeat(79)}`,
+  );
+
+  expect(tail).toContain("[phase log tail truncated to last 128 bytes]");
+  expect(tail).not.toContain("�");
+  expect(tail).toContain("y".repeat(79));
+});
