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

1 files changed, 15 insertions, 3 deletions

diff --git a/app/tests/test_backends_sglomni.py b/app/tests/test_backends_sglomni.py
index ebac500..8cb86cb 100644
--- a/app/tests/test_backends_sglomni.py
+++ b/app/tests/test_backends_sglomni.py
@@ -395,12 +395,24 @@ class HiggsConfigTests(unittest.TestCase):
         self.assertRegex(text, r"gpu_memory_fraction:\s*0\.80")
         # The engine's 2048-frame default (~27 s at 75 fps) silently
         # truncates a full 250-word sub-chunk; per-request values are
-        # clamped to this factory cap server-side.
-        self.assertRegex(text, r"max_new_tokens:\s*12288")
+        # clamped to this factory cap server-side. 3000 frames (~40 s)
+        # is the most the pinned 4095-token admission window allows
+        # after the prompt tokens.
+        self.assertRegex(text, r"max_new_tokens:\s*3000")
 
     def test_entry_sends_the_raised_frame_cap_per_request(self):
         entry = entry_by_key("higgs_audio_v3_tts")
-        self.assertEqual(entry.max_new_tokens, 12288)
+        self.assertEqual(entry.max_new_tokens, 3000)
+
+    def test_entry_caps_sub_requests_for_the_admission_window(self):
+        """The server pins prompt + generation at 4096 tokens for Higgs;
+        80 words (~30-40 s at 75 fps) narrates inside the 3000-frame
+        cap, and the pre-flight popup offers the clamp for a run."""
+        entry = entry_by_key("higgs_audio_v3_tts")
+        self.assertEqual(entry.chunk_words, 80)
+        # A full CHUNK_SIZE sub-chunk does NOT fit one Higgs request.
+        self.assertLess(entry.chunk_words, 250)
+        self.assertIsNone(entry_by_key("zonos2").chunk_words)
 
 
 class Fp8FallbackTests(unittest.TestCase):