fix: warn before using a likely too-big chunk size for sglang-omni models

1 files changed, 74 insertions, 1 deletions

diff --git a/app/converter/converter.py b/app/converter/converter.py
index 0769258..3b878c8 100644
--- a/app/converter/converter.py
+++ b/app/converter/converter.py
@@ -220,6 +220,73 @@ def prompt_overwrite(existing: List[Path], output_name: str,
         print("Please answer 'y' or 'n' (or press Enter for yes).")
 
 
+class ChunkClampCancelled(Exception):
+    """The chunk-cap popup's Cancel answer: the run stops unstarted."""
+
+
+def chunk_clamp_needed(entry) -> bool:
+    """True when ENTRY cannot narrate a full CHUNK_SIZE sub-request.
+
+    A catalog entry declares ``chunk_words`` when its engine's admission
+    window caps one request below what the configured CHUNK_SIZE can
+    narrate (Higgs: the server pins each request's prompt plus
+    generation at 4096 tokens).
+    """
+    return (entry is not None and entry.chunk_words is not None
+            and entry.chunk_words < config.CHUNK_SIZE)
+
+
+def chunk_clamp_message(entry) -> List[str]:
+    """The popup text for a chunk_words-capped ENTRY (short lines)."""
+    return [
+        f"{entry.label} can narrate at most ~{entry.chunk_words} words "
+        "per request: the server caps",
+        "each request's prompt plus generation at a fixed window. "
+        "Longer sub-chunks",
+        "may cut off mid-sentence.",
+    ]
+
+
+def prompt_chunk_clamp(entry, ask=None) -> Optional[int]:
+    """The per-run sub-request word cap for ENTRY (None = no clamp).
+
+    Models whose catalog entry declares ``chunk_words`` below CHUNK_SIZE
+    (Higgs) cannot narrate a full sub-chunk in one request; the popup
+    offers to clamp CHUNK_SIZE for this run, keep it ("try anyway",
+    risking mid-chunk truncation), or cancel the run. ASK, when given,
+    replaces the console prompt: it is called with (message lines, words)
+    and returns "clamp" or "anyway" (Cancel raises inside the callback —
+    the hub maps it to returning to the Generate form). A closed stdin
+    (non-interactive run) clamps: unattended runs keep working and never
+    produce silently truncated audio.
+    """
+    if not chunk_clamp_needed(entry):
+        return None
+    lines = chunk_clamp_message(entry)
+    if ask is not None:
+        answer = ask(lines, entry.chunk_words)
+        return entry.chunk_words if answer == "clamp" else None
+    for line in lines:
+        print(line)
+    while True:
+        try:
+            answer = input(
+                f"Set Chunk to {entry.chunk_words} for this run, try "
+                "anyway, or cancel? [S/t/c]: ").strip().lower()
+        except EOFError:
+            print(f"\n[WARNING] No interactive input available; clamping "
+                  f"sub-requests to {entry.chunk_words} words for this run")
+            return entry.chunk_words
+        if answer in ("", "s", "set"):
+            return entry.chunk_words
+        if answer in ("t", "try"):
+            return None
+        if answer in ("c", "cancel"):
+            raise ChunkClampCancelled(
+                "Conversion cancelled at the chunk-size prompt")
+        print("Please answer 's', 't', or 'c'.")
+
+
 class AudiobookConverter:
     """Audiobook converter using a local TTS API."""
 
@@ -236,6 +303,7 @@ class AudiobookConverter:
                  instructions: Optional[str] = None,
                  request_options: Optional[Dict[str, str]] = None,
                  api_url: Optional[str] = None,
+                 chunk_size: Optional[int] = None,
                  unload_models: Optional[bool] = None,
                  progress: Optional[Callable[[dict], None]] = None,
                  cancel=None):
@@ -324,13 +392,18 @@ class AudiobookConverter:
                         "catalog key for --model (see the backend docs).")
             model_id = entry.key
             self.model_id = model_id
+            # CHUNK_SIZE carries a per-run override (the pre-flight chunk
+            # popup's clamp for models whose engine caps one request below
+            # a full sub-chunk); None follows the config.CHUNK_SIZE setting.
+            self.chunk_size = chunk_size
             self.tts = SgOmniTTSClient(
                 chunks_dir=CHUNKS_FOLDER, model=model_id, voice=voice,
                 ref_audio=voice_clone_ref_audio,
                 ref_text=voice_clone_ref_text,
                 skip_transcription=skip_transcription,
                 instructions=instructions, language=self.language,
-                api_url=api_url, quiet=quiet, cancel=cancel)
+                api_url=api_url, chunk_size=self.chunk_size,
+                quiet=quiet, cancel=cancel)
         else:
             # Qwen: the voice mode picks the request shape (built-in
             # speaker, clone from a reference .wav, or a designed voice);