[Rebase] Align vLLM-Omni with vLLM v0.31.0 (#8459)

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>

tests/helpers/assertions.py

@@ -4,9 +4,11 @@
 """Assertion and response validation helpers for tests."""
 
 import base64
+import hashlib
 import io
 import json
 import math
+import os
 import tempfile
 import threading
 import wave
@@ -999,6 +1001,31 @@ def _assert_transcript_matches(
     )
 
 
+def _retain_failed_speech_audio(
+    audio_bytes: bytes | None, transcript: str, expected_text: Any, error: AssertionError
+) -> None:
+    """Retain the exact ASR input when a CI speech-content assertion fails."""
+    directory = os.environ.get("VLLM_OMNI_FAILED_SPEECH_AUDIO_DIR")
+    if not directory or not audio_bytes:
+        return
+    stem = f"failed_speech_{hashlib.sha256(audio_bytes).hexdigest()[:16]}"
+    root = Path(directory)
+    try:
+        root.mkdir(parents=True, exist_ok=True)
+        (root / f"{stem}.wav").write_bytes(audio_bytes)
+        (root / f"{stem}.json").write_text(
+            json.dumps(
+                {"transcript": transcript, "expected_text": str(expected_text), "assertion": str(error)},
+                ensure_ascii=False,
+                indent=2,
+            )
+        )
+        print(f"Retained failed speech ASR input: {root / f'{stem}.wav'}")
+    except OSError as exc:
+        # Diagnostic I/O must never replace or suppress the content failure.
+        print(f"Could not retain failed speech ASR input: {exc}")
+
+
 def assert_audio_speech_response(response: Any, request_config: dict[str, Any], run_level: str | None = None) -> None:
     """Validate speech API results from :class:`~tests.helpers.client.OmniResponse`.
 
@@ -1063,14 +1090,21 @@ def assert_audio_speech_response(response: Any, request_config: dict[str, Any],
             if expected_text:
                 print(f"audio content is: {transcript}")
                 print(f"input text is: {expected_text}")
-                _assert_transcript_matches(
-                    transcript,
-                    _speech_audio_for_transcription(getattr(response, "audio_bytes", None), request_config),
-                    expected_text,
-                    threshold=0.9,
-                    escalation_model=request_config.get("transcript_escalation_model"),
-                    language=request_config.get("transcript_language"),
+                transcription_audio = _speech_audio_for_transcription(
+                    getattr(response, "audio_bytes", None), request_config
                 )
+                try:
+                    _assert_transcript_matches(
+                        transcript,
+                        transcription_audio,
+                        expected_text,
+                        threshold=0.9,
+                        escalation_model=request_config.get("transcript_escalation_model"),
+                        language=request_config.get("transcript_language"),
+                    )
+                except AssertionError as exc:
+                    _retain_failed_speech_audio(transcription_audio, transcript, expected_text, exc)
+                    raise
         _assert_preset_voice_gender_from_audio(
             response.audio_bytes,
             request_config.get("voice"),