From 1da7906a5dcb6876d6e047d6e988f60432fb1271 Mon Sep 17 00:00:00 2001
From: Peter Steinberger <steipete@gmail.com>
Date: Mon, 2 Mar 2026 02:26:41 +0000
Subject: [PATCH] fix(line): land #31151 M4A voice MIME detection
 (@scoootscooob)

Landed from contributor PR #31151 by @scoootscooob.

Co-authored-by: scoootscooob <scoootscooob@users.noreply.github.com>
---
 CHANGELOG.md              |  1 +
 src/line/download.test.ts | 50 +++++++++++++++++++++++++++++++++++++++
 src/line/download.ts      | 19 +++++++++------
 3 files changed, 63 insertions(+), 7 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 47081ae8eac..a5a4e5aefd2 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -21,6 +21,7 @@ Docs: https://docs.openclaw.ai
 ### Fixes
 
 - Windows/Plugin install: avoid `spawn EINVAL` on Windows npm/npx invocations by resolving to `node` + npm CLI scripts instead of spawning `.cmd` directly. Landed from contributor PR #31147 by @codertony. Thanks @codertony.
+- LINE/Voice transcription: classify M4A voice media as `audio/mp4` (not `video/mp4`) by checking the MPEG-4 `ftyp` major brand (`M4A ` / `M4B `), restoring voice transcription for LINE voice messages. Landed from contributor PR #31151 by @scoootscooob. Thanks @scoootscooob.
 - Agents/Thinking fallback: when providers reject unsupported thinking levels without enumerating alternatives, retry with `think=off` to avoid hard failure during model/provider fallback chains. Landed from contributor PR #31002 by @yfge. Thanks @yfge.
 - Agents/Failover reason classification: avoid false rate-limit classification from incidental `tpm` substrings by matching TPM as a standalone token/phrase and keeping auth-context errors on the auth path. Landed from contributor PR #31007 by @HOYALIM. Thanks @HOYALIM.
 - Slack/Announce target account routing: enable session-backed announce-target lookup for Slack so multi-account announces resolve the correct `accountId` instead of defaulting to bot-token context. Landed from contributor PR #31028 by @taw0002. Thanks @taw0002.
diff --git a/src/line/download.test.ts b/src/line/download.test.ts
index 677f2049200..ea9a236867f 100644
--- a/src/line/download.test.ts
+++ b/src/line/download.test.ts
@@ -66,4 +66,54 @@ describe("downloadLineMedia", () => {
     await expect(downloadLineMedia("mid", "token", 7)).rejects.toThrow(/Media exceeds/i);
     expect(writeSpy).not.toHaveBeenCalled();
   });
+
+  it("detects M4A audio from ftyp major brand (#29751)", async () => {
+    // Real M4A magic bytes: size(4) + "ftyp" + "M4A "
+    const m4a = Buffer.from([
+      0x00,
+      0x00,
+      0x00,
+      0x1c, // box size
+      0x66,
+      0x74,
+      0x79,
+      0x70, // "ftyp"
+      0x4d,
+      0x34,
+      0x41,
+      0x20, // "M4A " major brand
+    ]);
+    getMessageContentMock.mockResolvedValueOnce(chunks([m4a]));
+    vi.spyOn(fs.promises, "writeFile").mockResolvedValueOnce(undefined);
+
+    const result = await downloadLineMedia("mid-m4a", "token");
+
+    expect(result.contentType).toBe("audio/mp4");
+    expect(result.path).toMatch(/\.m4a$/);
+  });
+
+  it("detects MP4 video from ftyp major brand (isom)", async () => {
+    // MP4 video magic bytes: size(4) + "ftyp" + "isom"
+    const mp4 = Buffer.from([
+      0x00,
+      0x00,
+      0x00,
+      0x1c,
+      0x66,
+      0x74,
+      0x79,
+      0x70,
+      0x69,
+      0x73,
+      0x6f,
+      0x6d, // "isom" major brand
+    ]);
+    getMessageContentMock.mockResolvedValueOnce(chunks([mp4]));
+    vi.spyOn(fs.promises, "writeFile").mockResolvedValueOnce(undefined);
+
+    const result = await downloadLineMedia("mid-mp4", "token");
+
+    expect(result.contentType).toBe("video/mp4");
+    expect(result.path).toMatch(/\.mp4$/);
+  });
 });
diff --git a/src/line/download.ts b/src/line/download.ts
index ceb6916a525..29f01258794 100644
--- a/src/line/download.ts
+++ b/src/line/download.ts
@@ -80,15 +80,20 @@ function detectContentType(buffer: Buffer): string {
     ) {
       return "image/webp";
     }
-    // MP4
-    if (buffer[4] === 0x66 && buffer[5] === 0x74 && buffer[6] === 0x79 && buffer[7] === 0x70) {
-      return "video/mp4";
-    }
-    // M4A/AAC
-    if (buffer[0] === 0x00 && buffer[1] === 0x00 && buffer[2] === 0x00) {
-      if (buffer[4] === 0x66 && buffer[5] === 0x74 && buffer[6] === 0x79 && buffer[7] === 0x70) {
+    // MPEG-4 container (ftyp box) — distinguish audio (M4A) from video (MP4)
+    // by checking the major brand at bytes 8-11.
+    if (
+      buffer.length >= 12 &&
+      buffer[4] === 0x66 &&
+      buffer[5] === 0x74 &&
+      buffer[6] === 0x79 &&
+      buffer[7] === 0x70
+    ) {
+      const brand = String.fromCharCode(buffer[8], buffer[9], buffer[10], buffer[11]);
+      if (brand === "M4A " || brand === "M4B ") {
         return "audio/mp4";
       }
+      return "video/mp4";
     }
   }