Podcast mode: notes read aloud with a lyric-style word highlight

The third segment of the note-powered wizards (Study deck / Homework /
Podcast) takes the same intake - photos, documents, pasted text, the share
target - and turns it into a spoken episode.

- prompts: PODCAST_SYSTEM_PROMPT writes for the ear (plain prose, no markdown,
  no visual references), chaptered into 3-8 sections around a length target.
- /api/podcast mirrors /api/generate's plumbing (rate limit, model gate,
  provider keys, heartbeats, the 2x deadline, the optional vision pass).
- storage: frezmo.podcasts.v1, zod-validated, included in the backup and the
  encrypted sync payload; a new library tab lists episodes with listen /
  rename / delete-with-undo, and the wizard switch deep-links in.
- player: the transcript is word-wrapped spans and the word under the voice
  rides a lyric-style highlight that keeps itself centred. Two clocks: exact
  onboundary events where the browser reports them, a per-word length timer
  where it does not (iOS Safari); the first boundary retires the timer.
  Pause = cancel + re-speak from the word, which makes resume, chapter jumps
  and tap-any-word-to-seek the same operation; the position saves on pause,
  page-hide and unmount, so reopening resumes. Speed rebuilds the engine and
  keeps playing; the Aero soundtrack pauses itself when the voice starts; a
  browser with no voice gets an honest note and a readable transcript.
- the script sits on a glass pane (plain paragraphs over Aero's grass failed
  contrast; the scan now covers the player too).

tests/podcast-test.mjs (17th suite) stubs the model and the speech engine and
drives the highlight by hand: 26 checks. All suites green, contrast clean.
Version 0.7.3, SW v95.

lib/ai.ts

@@ -20,6 +20,8 @@ import {
   HOMEWORK_CHECK_SYSTEM_PROMPT,
   HOMEWORK_GUIDE_SYSTEM_PROMPT,
   HOMEWORK_MAKE_SYSTEM_PROMPT,
+  PODCAST_SYSTEM_PROMPT,
+  buildPodcastUserPrompt,
   REFINE_SYSTEM_PROMPT,
   VISION_SYSTEM_PROMPT,
   VISION_USER_INSTRUCTION,
@@ -27,6 +29,7 @@ import {
 import {
   extractedNotesSchema,
   generatedActivitySchema,
+  generatedPodcastSchema,
   gradeResultSchema,
   homeworkCheckSchema,
   homeworkMakeSchema,
@@ -38,6 +41,7 @@ import {
   type HomeworkCheck,
   type HomeworkGuide,
   type HomeworkMake,
+  type GeneratedPodcast,
 } from "./schemas";
 import { parseJsonLoose } from "./utils";
 import type { OllamaAuth } from "./config";
@@ -401,6 +405,58 @@ export async function generateActivities(input: {
   return { deck: value, requested };
 }
 
+/* ------------------------------------------------------------------ */
+/* Podcast                                                             */
+/* ------------------------------------------------------------------ */
+
+const PODCAST_SHAPE_HINT = `{"title":"Nothing but the sky","language":"English","summary":"One sentence.","sections":[{"heading":"Why blue","text":"Sixty to a hundred and forty words of narration."}]}`;
+
+export async function generatePodcast(input: {
+  model: string;
+  auth: OllamaAuth;
+  provider?: ProviderTarget;
+  notes: string;
+  minutes: number;
+  language?: string;
+  focus?: string;
+  signal?: AbortSignal;
+}): Promise<{ podcast: GeneratedPodcast }> {
+  const minutes = Math.min(Math.max(input.minutes, 1), 15);
+  const { value } = await runJsonStep<GeneratedPodcast>({
+    model: input.model,
+    auth: input.auth,
+    provider: input.provider,
+    system: PODCAST_SYSTEM_PROMPT,
+    user: buildPodcastUserPrompt({
+      notes: input.notes,
+      minutes,
+      language: input.language,
+      focus: input.focus,
+    }),
+    /* One usable section beats a retry loop: the repair pass fills gaps. */
+    validate: (parsed) => {
+      const result = generatedPodcastSchema.safeParse(parsed);
+      if (!result.success) return { ok: false as const, error: summariseZodError(result.error) };
+      const sections = result.data.sections
+        .map((section) => ({
+          heading: section.heading.trim(),
+          text: section.text.trim().replace(/\s+/g, " "),
+        }))
+        .filter((section) => section.text.length > 0);
+      if (sections.length === 0) {
+        return { ok: false as const, error: "No sections with spoken text were found." };
+      }
+      return { ok: true as const, value: { ...result.data, sections } };
+    },
+    shapeHint: PODCAST_SHAPE_HINT,
+    label: "Writing the script",
+    signal: input.signal,
+    temperature: 0.75,
+  });
+
+  return { podcast: value };
+}
+
 /* ------------------------------------------------------------------ */
 /* Grading                                                             */
 /* ------------------------------------------------------------------ */