Add combined all-languages chapter to the renderer

Writes _ALL_LANGUAGES_full_sample.wav alongside the per-language chapters,
English first then the operator's list order, so the whole 10-language set
can be heard in one pass (17.8 min for the sample chapter).

Root cause found while rendering with 1.7B: the ICL prompt path is what
blows up memory, not model size or uptime. A single prompt_slug request
added ~14 GB (7.2 -> 21.6 GB) and wedged the server, after which the
otherwise-stable ref_audio path also hung. A fresh 1.7B loads in 8s at
5.4 GB, generates in 9-16s per clip, and settles at ~37 MB per additional
clip (13.1 GB after 120) with no restart needed between languages.

The 0.6B render is kept in Lang_test_0p6B for comparison; the 1.7B render
is in Lang_test.

Suite: 721 passed, 8 pre-existing.

scripts/render_lang_test.py

@@ -10,6 +10,10 @@ per-language file, which is what you actually listen to.
 Qwen3-TTS auto-detects language from the text - ``/v1/tts`` takes no language
 argument - so there is nothing to set per clip.
 
+Also writes ``_ALL_LANGUAGES_full_sample.wav`` - every language back to back,
+in the operator's list order with English first - for listening to the whole
+set in one pass.
+
 Voice is supplied two ways:
 
 ``--voice-mode ref`` (default) sends ``ref_audio`` + ``ref_text`` and lets the
@@ -168,6 +172,33 @@ def stitch(parts: list[Path], out: Path, gap_ms: int = 400) -> None:
     listing.unlink(missing_ok=True)
 
 
+# English first, then the operator's stated order for the languages rendered.
+COMBINED_ORDER = ["EN", "ZH", "JA", "KO", "DE", "ES", "FR", "RU", "IT", "PT"]
+
+
+def build_combined(out_root: Path) -> Path | None:
+    """Concatenate every per-language chapter into one listenable file."""
+    import subprocess
+
+    lines = []
+    for lang in COMBINED_ORDER:
+        f = out_root / lang / f"_full_sample_{lang}.wav"
+        if f.exists():
+            lines.append(f"file '{f.resolve()}'")
+    if not lines:
+        return None
+    listing = out_root / "._combined.txt"
+    listing.write_text("\n".join(lines) + "\n")
+    out = out_root / "_ALL_LANGUAGES_full_sample.wav"
+    subprocess.run(
+        ["ffmpeg", "-y", "-f", "concat", "-safe", "0", "-i", str(listing),
+         "-c", "copy", str(out)],
+        check=True, capture_output=True,
+    )
+    listing.unlink(missing_ok=True)
+    return out
+
+
 def main() -> int:
     ap = argparse.ArgumentParser(description=__doc__)
     ap.add_argument("--project")
@@ -270,7 +301,10 @@ def main() -> int:
         except Exception as e:  # stitching is a convenience, not the deliverable
             print(f"  {suffix}: stitch failed: {e}")
 
+    combined = build_combined(out_root)
     print(f"\n  done: {ok} rendered, {failed} failed")
+    if combined:
+        print(f"  combined: {combined}")
     return 0 if ok else 1