Merge image edit titles in the user's language

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MRtGG9ARfqqhma3t85Ro2u

packages/adapters/src/media/image-operations.test.ts

@@ -223,6 +223,13 @@ describe("image operations", () => {
     expect((await sharp(outputs[0]!.path).metadata()).format).toBe("webp");
     expect(result.summary).toBe("Edited photo.jpg into photo-edit.webp (1080×1920).");
     expect(emulator.requests).toHaveLength(0);
+    const titled = await run(
+      operation,
+      "edit_image",
+      { artifactId: "photo-1", title: "Titelbild: Sommer", rotate: 180 },
+      { "photo-1": photo },
+    );
+    expect(titled.outputs[0]?.name).toBe("Titelbild Sommer.jpg");
     await expect(
       run(operation, "edit_image", { artifactId: "photo-1", prompt: "snow" }, { "photo-1": photo }),
     ).rejects.toThrow("ComfyUI is not configured");
@@ -267,7 +274,17 @@ describe("helpers", () => {
         resize: { aspect: "vertical", fit: "crop" },
         format: "png",
       }),
-    ).toBe("crop · 90° · 9:16 · PNG");
+    ).toBe("1×1 · 90° · 9:16 · PNG");
+    expect(
+      editImageTitle({
+        artifactId: "a",
+        flip: "vertical",
+        extend: { top: 4, right: 0, bottom: 0, left: 0 },
+      }),
+    ).toBe("↕");
+    expect(
+      editImageTitle({ artifactId: "a", title: "Titelbild", prompt: "snow", rotate: 90 }),
+    ).toBe("Titelbild");
     expect(editImageTitle({ artifactId: "a", resize: { width: 800, fit: "crop" } })).toBe("800×…");
     expect(editImageTitle({ artifactId: "a", prompt: "make it snow" })).toBe("make it snow");
   });

packages/adapters/src/media/image-operations.ts

@@ -36,6 +36,7 @@ import {
   imageSize,
   sharpAvailable,
 } from "./image-edit.js";
+import { cleanFileName } from "./video-operations.js";
 
 /** Free GPU memory a generation needs before it starts; fixed, so a custom workflow cannot lower it. */
 export const IMAGE_GENERATION_MIN_VRAM_MB = 6_000;
@@ -75,19 +76,22 @@ export function fileStem(text: string, fallback: string): string {
   return words?.slice(0, 6).join("-").slice(0, 48).replace(/-+$/, "") || fallback;
 }
 
-/** Short card title for an edit without a prompt, such as "crop · 9:16 · PNG". */
+/**
+ * Card title: the bot's title or repaint prompt, else language-neutral tokens for what the edit
+ * does, such as "300×300 · 90° · ↔ · 9:16 · PNG".
+ */
 export function editImageTitle(input: EditImageInput): string {
+  if (input.title) return input.title;
   if (input.prompt) return input.prompt;
-  const { resize } = input;
+  const { crop, resize } = input;
   const parts = [
-    input.crop && "crop",
+    crop && `${crop.width}×${crop.height}`,
     input.rotate && `${input.rotate}°`,
-    input.flip && "flip",
+    input.flip && (input.flip === "horizontal" ? "↔" : "↕"),
     resize &&
       (resize.aspect
         ? MEDIA_PRESETS[resize.aspect].aspect
         : `${resize.width ?? "…"}×${resize.height ?? "…"}`),
-    input.extend && "extend",
     input.format?.toUpperCase(),
   ];
   return parts.filter(Boolean).join(" · ");
@@ -256,8 +260,10 @@ async function editImage(
   const format = input.format ?? defaultFormat(source.mimeType);
   const encoded = await encodeImage(png, format);
   const mimeType = IMAGE_FORMAT_MIME_TYPES[format];
-  const stem = source.name.replace(/\.[^.]+$/, "") || "image";
-  const name = `${stem}-edit${attachmentExtensionForMimeType(mimeType)}`;
+  const stem = input.title
+    ? cleanFileName(input.title, "image")
+    : `${cleanFileName(source.name.replace(/\.[^.]+$/, ""), "image")}-edit`;
+  const name = `${stem}${attachmentExtensionForMimeType(mimeType)}`;
   const path = join(context.tempDir, name);
   await writeFile(path, encoded.bytes);
   await context.addOutput({

packages/contracts/src/media-generation.ts

@@ -1,6 +1,7 @@
 import * as z from "zod";
 import { Id } from "./ids.js";
 import { MediaFitSchema, MediaPresetIdSchema } from "./media.js";
+import { MediaTitleSchema } from "./media-video.js";
 
 export const MEDIA_IMAGE_MAX_COUNT = 4;
 export const MEDIA_VIDEO_MAX_SECONDS = 10;
@@ -55,6 +56,9 @@ export type ImageFormat = z.infer<typeof ImageFormatSchema>;
 export const EditImageInputSchema = z
   .object({
     artifactId: Id.describe("Image artifact to edit."),
+    title: MediaTitleSchema.optional().describe(
+      "A few words in the user's language for the card and file name.",
+    ),
     crop: z
       .object({ left: Pixels, top: Pixels, width: Pixels.min(1), height: Pixels.min(1) })
       .optional()

packages/contracts/src/media-video.ts

@@ -14,7 +14,7 @@ const TimeRangeSchema = z
   .refine((range) => range.end > range.start, "end must be after start");
 
 /** Written by the bot in the user's language; shown on the media card and used as file name. */
-const MediaTitleSchema = z.string().trim().min(1).max(120);
+export const MediaTitleSchema = z.string().trim().min(1).max(120);
 
 export const EditVideoStepSchema = z.discriminatedUnion("op", [
   z