feat(media): title transcription cards with what they transcribe

A card that only says "Transcript" does not tell two transcriptions apart,
and it is English whatever the user's language.

- transcribe takes an optional title like the video operations, so a bot
  names the card in the user's language; "Transcript" stays the default.
- Transcribe on a media card passes the source file name as the title.
- The E2E seeds the card through bootstrap as well as threads/get, since the
  bot thread's first snapshot arrives with bootstrap.

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

apps/web/e2e/media-card.spec.ts

@@ -11,6 +11,7 @@ import {
 
 type MediaBlock = Record<string, unknown> & { kind: "media" };
 type Snapshot = {
+  botId?: string;
   threadId: string;
   messages: Array<{ seq: number } & Record<string, unknown>>;
 };
@@ -59,31 +60,36 @@ async function stillPngBase64(page: Page): Promise<string> {
 
 /**
  * Media jobs run on a GPU server or ffmpeg that CI does not have, so the card is seeded: real
- * artifacts are uploaded, and the thread snapshot carries a bot message with the job's card.
+ * artifacts are uploaded, and the bot thread's snapshot (from bootstrap on load, threads/get on
+ * refresh) carries a bot message with the job's card.
  */
 async function seedMediaMessage(page: Page, botId: string, block: () => MediaBlock) {
-  await page.route("**/rpc/threads/get", async (route) => {
-    const fetched = await fetchRpcEnvelope(route);
-    const snapshot = fetched.body.json as (Snapshot & { botId?: string }) | undefined;
-    if (snapshot?.botId === botId) {
-      const seq = Math.max(0, ...snapshot.messages.map((message) => message.seq)) + 1;
-      snapshot.messages.push({
-        id: `media-message-${seq}`,
-        threadId: snapshot.threadId,
-        seq,
-        role: "bot",
-        botId,
-        blocks: [block()],
-        createdAt: new Date().toISOString(),
-      });
-    }
-    // Fresh headers: the original content length no longer matches the patched body.
-    await route.fulfill({
-      status: fetched.status,
-      contentType: "application/json",
-      body: JSON.stringify(fetched.body),
+  const seed = (snapshot: Snapshot | undefined) => {
+    if (snapshot?.botId !== botId) return;
+    const seq = Math.max(0, ...snapshot.messages.map((message) => message.seq)) + 1;
+    snapshot.messages.push({
+      id: `media-message-${seq}`,
+      threadId: snapshot.threadId,
+      seq,
+      role: "bot",
+      botId,
+      blocks: [block()],
+      createdAt: new Date().toISOString(),
     });
-  });
+  };
+  for (const procedure of ["bootstrap", "threads/get"]) {
+    await page.route(`**/rpc/${procedure}`, async (route) => {
+      const fetched = await fetchRpcEnvelope(route);
+      const json = fetched.body.json as (Snapshot & { thread?: Snapshot }) | undefined;
+      seed(procedure === "bootstrap" ? json?.thread : json);
+      // Fresh headers: the original content length no longer matches the patched body.
+      await route.fulfill({
+        status: fetched.status,
+        contentType: "application/json",
+        body: JSON.stringify(fetched.body),
+      });
+    });
+  }
 }
 
 test("renders a media job card while it runs and when it is done", async ({ page }, testInfo) => {
@@ -168,13 +174,7 @@ test("renders a media job card while it runs and when it is done", async ({ page
       body: JSON.stringify({ json: { jobId: "media-job-2", messageId: "media-message-next" } }),
     });
   });
-  const seeded = page.waitForResponse(
-    async (response) =>
-      response.url().includes("/rpc/threads/get") &&
-      (await response.text()).includes("media-job-1"),
-  );
   await page.reload();
-  await seeded;
 
   const card = page.getByTestId("media-card");
   await expect(card).toBeVisible({ timeout: 30_000 });
@@ -206,6 +206,6 @@ test("renders a media job card while it runs and when it is done", async ({ page
     botId,
     messageId: expect.stringMatching(/^media-message-\d+$/),
     operation: "transcribe",
-    input: { artifactId: voice.id },
+    input: { artifactId: voice.id, title: "voice-note.wav" },
   });
 });

apps/web/src/components/media/MediaCard.tsx

@@ -32,7 +32,7 @@ const CARD_CLASS =
 
 export type MediaCardAction =
   | { kind: "export"; artifactId: string; preset: MediaPresetId }
-  | { kind: "transcribe"; artifactId: string }
+  | { kind: "transcribe"; artifactId: string; name: string }
   | { kind: "cancel" };
 
 /** Which follow-up jobs the space can run; actions it cannot run are not offered. */
@@ -156,7 +156,9 @@ function OutputActions({
           variant="outline"
           size="sm"
           disabled={busy}
-          onClick={() => onAction({ kind: "transcribe", artifactId: output.artifactId })}
+          onClick={() =>
+            onAction({ kind: "transcribe", artifactId: output.artifactId, name: output.name })
+          }
         >
           <Captions />
           {t`Transcribe`}
@@ -378,7 +380,11 @@ export function MediaCard({
             operation: "export_video",
             input: { artifact_id: action.artifactId, presets: [action.preset] },
           }
-        : { operation: "transcribe", input: { artifactId: action.artifactId } }),
+        : // The new card is titled with the file it transcribes.
+          {
+            operation: "transcribe",
+            input: { artifactId: action.artifactId, title: action.name },
+          }),
     });
   };
   return <MediaCardView block={block} target={target} available={available} onAction={onAction} />;

packages/adapters/src/media/transcription.test.ts

@@ -201,6 +201,7 @@ describe("transcribe operation", () => {
     const input = registration.inputSchema.parse({ artifactId: "audio-1", language: "de" });
     expect(registration.artifactIds?.(input)).toEqual(["audio-1"]);
     expect(registration.title(input)).toBe("Transcript");
+    expect(registration.title({ ...input, title: "voice-note.wav" })).toBe("voice-note.wav");
     expect(
       registration.inputSchema.safeParse({ artifactId: "audio-1", language: "German!" }).success,
     ).toBe(false);

packages/adapters/src/media/transcription.ts

@@ -146,7 +146,7 @@ export function createTranscriptionOperations(
     {
       operation: "transcribe",
       inputSchema: TranscribeInputSchema,
-      title: () => "Transcript",
+      title: (input) => input.title ?? "Transcript",
       available: async () => Boolean((await deps.loadSettings()).transcription),
       artifactIds: (input) => [input.artifactId],
       handler: {

packages/contracts/src/media-transcription.ts

@@ -9,5 +9,12 @@ export const TranscribeInputSchema = z.object({
     .regex(/^[A-Za-z]{2,3}(-[A-Za-z0-9]{2,8})*$/, "Use a language code such as en or de")
     .optional()
     .describe("Spoken language as a code such as en or de; detected when omitted."),
+  title: z
+    .string()
+    .trim()
+    .min(1)
+    .max(120)
+    .optional()
+    .describe("A few words in the user's language for the media card."),
 });
 export type TranscribeInput = z.infer<typeof TranscribeInputSchema>;