Bigger decks: pick up to 30 activities, built in batches

The create wizard stopped at 15 activities because the API, the prompt and
the salvage path all capped at 18: one reply must be one valid JSON object,
and past ~18 activities models truncate or drop cards. Raising the cap alone
would have shipped decks that came back short.

- The count picker offers 8 / 10 / 12 / 15 / 20 / 30; a deck's "add more" row
  gained +15. The help line says bigger decks take longer.
- /api/generate accepts up to 30 (FREEZMO_DEFAULT_ACTIVITY_COUNT now clamps
  to 30 as well) and sizes its overall deadline from the number of model
  calls instead of a fixed two.
- generateActivities splits anything above 18 evenly across calls (30 → 15 +
  15, 25 → 13 + 12) and merges them into one deck. The first call keeps the
  "add to this deck" contract; later calls are told the title, the types
  already used and the topics already covered. A normalised content signature
  drops a card that repeats an earlier one, so the same idea never ships
  twice. requested/generated still travel in the stream meta.
- phase1-test: a stub Ollama answers two 15-card batches (the second repeats
  one card on purpose) → two calls, the even split, the "already covered"
  prompt, 29 merged cards, the duplicate shipped once, title from the first
  reply, and count 31 answered 400 (59 checks).
- wizard-test: the picker offers 30, the wizard sends count: 30, and the
  30-card deck is stored and opened (99 checks).

Version 0.8.4, SW v106.

app/api/generate/route.ts

@@ -1,6 +1,6 @@
 import { z } from "zod";
 
-import { extractNotes, generateActivities, notesToText, type PipelineStage } from "@/lib/ai";
+import { activityBatches, extractNotes, generateActivities, notesToText, type PipelineStage } from "@/lib/ai";
 import { getServerConfig, resolveModelName } from "@/lib/config";
 import { INERT_OLLAMA_AUTH, resolveModelTarget } from "@/lib/providers-server";
 import { friendlyErrorMessage, OllamaError } from "@/lib/ollama";
@@ -26,7 +26,8 @@ const requestSchema = z.object({
   images: z.array(dataUrlSchema(MAX_IMAGE_CHARS)).max(16).optional(),
   text: z.string().max(120_000).optional(),
   difficulty: difficultySchema.default("medium"),
-  count: z.number().int().min(4).max(18).optional(),
+  /** One deck; a big count is built in several model calls (lib/ai.ts). */
+  count: z.number().int().min(4).max(30).optional(),
   focus: z.string().max(300).optional(),
   /** Language the deck must be written in (usually detected by the vision step). */
   language: z.string().max(60).optional(),
@@ -129,8 +130,10 @@ export async function POST(request: Request) {
   const requestedCount = count ?? config.defaultActivityCount;
   const encode = encoder();
   const abort = new AbortController();
-  // A single hard deadline for the whole pipeline (two sequential model calls).
-  const globalTimer = setTimeout(() => abort.abort(), config.timeoutMs * 2);
+  // A single hard deadline for the whole pipeline: the vision step (when there
+  // are photos) plus one model call per activity batch.
+  const modelCalls = activityBatches(requestedCount).length + 1;
+  const globalTimer = setTimeout(() => abort.abort(), config.timeoutMs * modelCalls);
   const onRequestAbort = () => abort.abort();
   if (request.signal.aborted) abort.abort();
   else request.signal.addEventListener("abort", onRequestAbort, { once: true });