Pin the continuation seed so the app reproduces the verified take

SA3 is generative: app.py called continue_audio with the default seed (-1),
drawing a fresh random seed every run, so each continuation differed and most
were weaker than the lab take Tony approved. The verified lab_out/sa3 renders
were produced by lab_e2e.py with seed=7; pin the same seed in the app's
generation call so the deliverable reproduces that result instead of
re-rolling. No audio-pipeline parameters changed.

app.py

@@ -128,9 +128,13 @@ def finish_song(audio_path, total_seconds, vibe, remaster,
             progress(frac, desc=desc)
 
     try:
+        # Pin the seed to the lab's known-good draw. SA3 is generative: a
+        # random seed gives a different (and often weaker) continuation every
+        # run. seed=7 is the draw that produced the verified lab_out/sa3 takes,
+        # so the app reproduces that result instead of re-rolling each time.
         new_tail, source_seconds, SR = engine.continue_audio(
             listen_path, total_seconds=total_seconds,
-            prompt=(vibe or "").strip(), progress=_on_stage)
+            prompt=(vibe or "").strip(), seed=7, progress=_on_stage)
     except ValueError as e:
         # e.g. the clip is too long to continue under the 120s cap
         raise gr.Error(str(e))