Reject task=translate on the server for models that cannot translate (D-044)

The UI already hid it; a direct API call to POST /api/transcribe or the live
WebSocket could still get the source language back labelled as a translation.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

docs/WorkBreakdown.md

@@ -427,8 +427,9 @@ Found while building transcript translation (D-045), 2026-10-29:
       every row of a padded batch, so translation runs one sentence per call
       (~4× slower than batch 8 would be). Re-check after the 4.3 upgrade with
       `bun scripts/bench-translate.ts` ("output identical" across batch sizes).
-- [ ] The server API still accepts `task: "translate"` with large-v3-turbo
-      (only the UI hides it, D-044).
+- [x] The server API still accepts `task: "translate"` with large-v3-turbo
+      (only the UI hides it, D-044). — Fixed: `POST /api/transcribe` and the
+      live WebSocket answer 400 via `translateNotSupported` (src/server/transcribe.ts).
 
 Found in spec 001 workstream 6 (D-046), open:
 - [ ] Transformers.js 4.2 has no beam search: `num_beams > 1` in a model's