From 648c8c12f5eda78dcc3cd467937468b4507837b4 Mon Sep 17 00:00:00 2001
From: SnapOtter <snapotter.hq@gmail.com>
Date: Wed, 13 May 2026 14:18:49 +0800
Subject: [PATCH] fix: convert input buffer to PNG before passing to face
 landmarks Python sidecar

AVIF (and other Sharp-native formats) were written as raw bytes to a
.png temp file, causing PIL to fail with "cannot identify image file".
Every other AI module wrapper already converts via sharp().png().toBuffer()
before writing; face-landmarks was the only one that skipped this step.
---
 packages/ai/src/face-landmarks.ts    | 4 +++-
 tests/unit/ai/face-landmarks.test.ts | 7 ++++---
 tests/unit/ai/tools.test.ts          | 8 +++++---
 tests/unit/api/ai-tools.test.ts      | 6 +++---
 4 files changed, 15 insertions(+), 10 deletions(-)

diff --git a/packages/ai/src/face-landmarks.ts b/packages/ai/src/face-landmarks.ts
index 02913c9c..b42d1411 100644
--- a/packages/ai/src/face-landmarks.ts
+++ b/packages/ai/src/face-landmarks.ts
@@ -1,6 +1,7 @@
 import { unlink, writeFile } from "node:fs/promises";
 import { tmpdir } from "node:os";
 import { join } from "node:path";
+import sharp from "sharp";
 import { type ProgressCallback, parseStdoutJson, runPythonWithProgress } from "./bridge.js";
 
 export interface FaceLandmarkPoint {
@@ -33,7 +34,8 @@ export async function detectFaceLandmarks(
   const inputPath = join(tmpdir(), `face_landmarks_${Date.now()}.png`);
 
   try {
-    await writeFile(inputPath, inputBuffer);
+    const pngBuffer = await sharp(inputBuffer).png().toBuffer();
+    await writeFile(inputPath, pngBuffer);
     const { stdout } = await runPythonWithProgress(
       "face_landmarks.py",
       [inputPath, "unused", "{}"],
diff --git a/tests/unit/ai/face-landmarks.test.ts b/tests/unit/ai/face-landmarks.test.ts
index 4f866de4..2b586949 100644
--- a/tests/unit/ai/face-landmarks.test.ts
+++ b/tests/unit/ai/face-landmarks.test.ts
@@ -68,13 +68,14 @@ describe("detectFaceLandmarks", () => {
       );
     });
 
-    it("writes input buffer directly without sharp conversion", async () => {
+    it("converts input buffer to PNG before writing", async () => {
+      const sharp = (await import("sharp")).default;
       await detectFaceLandmarks(FAKE_INPUT);
 
-      // face-landmarks.ts does NOT use sharp -- it writes inputBuffer directly
+      expect(sharp).toHaveBeenCalledWith(FAKE_INPUT);
       expect(writeFile).toHaveBeenCalledWith(
         expect.stringContaining("face_landmarks_"),
-        FAKE_INPUT,
+        Buffer.from("mock-png-data"),
       );
     });
 
diff --git a/tests/unit/ai/tools.test.ts b/tests/unit/ai/tools.test.ts
index 8d713c22..6bcf5d41 100644
--- a/tests/unit/ai/tools.test.ts
+++ b/tests/unit/ai/tools.test.ts
@@ -580,11 +580,13 @@ describe("detectFaceLandmarks", () => {
     expect(result.landmarks).toBeNull();
   });
 
-  it("does not use sharp to convert to PNG (writes buffer directly)", async () => {
+  it("converts input buffer to PNG before writing", async () => {
     await detectFaceLandmarks(FAKE_INPUT);
 
-    // face-landmarks writes inputBuffer directly, no sharp conversion
-    expect(writeFile).toHaveBeenCalledWith(expect.stringContaining("face_landmarks_"), FAKE_INPUT);
+    expect(writeFile).toHaveBeenCalledWith(
+      expect.stringContaining("face_landmarks_"),
+      Buffer.from("mock-png-data"),
+    );
   });
 
   it("cleans up temp file in finally block", async () => {
diff --git a/tests/unit/api/ai-tools.test.ts b/tests/unit/api/ai-tools.test.ts
index b427071d..559c7921 100644
--- a/tests/unit/api/ai-tools.test.ts
+++ b/tests/unit/api/ai-tools.test.ts
@@ -630,13 +630,13 @@ describe("detectFaceLandmarks", () => {
     await expect(detectFaceLandmarks(INPUT_BUFFER)).rejects.toThrow("MediaPipe not found");
   });
 
-  it("writes raw input buffer (no sharp conversion)", async () => {
+  it("converts input buffer to PNG before writing", async () => {
     mockParseStdoutJson.mockReturnValue({ success: true, faceDetected: false });
 
     await detectFaceLandmarks(INPUT_BUFFER);
 
-    // face-landmarks writes inputBuffer directly, no sharp pipeline
-    expect(mockWriteFile).toHaveBeenCalledWith(expect.any(String), INPUT_BUFFER);
+    expect(mockSharp).toHaveBeenCalledWith(INPUT_BUFFER);
+    expect(mockWriteFile).toHaveBeenCalledWith(expect.any(String), Buffer.from("mock-png"));
   });
 });