ops: add isolated ASR deployment and safe GPU test handoff

deployment/followup-audio-asr/cpu_preflight.py

@@ -0,0 +1,61 @@
+#!/usr/bin/env python3
+"""CPU-only dependency, format and route checks. Does not instantiate a model."""
+import importlib.metadata as metadata
+import io
+import json
+from pathlib import Path
+import numpy as np
+import soundfile as sf
+import soxr
+import scipy
+import av
+import vllm
+import torch
+from transformers import WhisperFeatureExtractor
+
+signal=np.zeros(16000,dtype=np.float32)
+encoded=io.BytesIO()
+sf.write(encoded,signal,16000,format='WAV')
+encoded.seek(0)
+decoded,rate=sf.read(encoded,dtype='float32')
+assert rate==16000 and decoded.shape==(16000,)
+resampled=soxr.resample(decoded,16000,8000)
+assert len(resampled)==8000
+features=WhisperFeatureExtractor()(decoded,sampling_rate=rate,return_tensors='np')
+assert features['input_features'].shape[0]==1
+root=Path(vllm.__file__).parent
+model_source=(root/'model_executor/models/qwen3_asr.py').read_text()
+registry_source=(root/'model_executor/models/registry.py').read_text()
+assert 'Qwen3ASRForConditionalGeneration' in registry_source
+assert 'SupportsTranscription' in model_source
+routes=[str(path.relative_to(root)) for path in (root/'entrypoints').rglob('*.py') if '"/v1/audio/transcriptions"' in path.read_text()]
+assert routes, 'Transcription route missing'
+assert not Path('/dev/nvidia0').exists(), 'This test must not have GPU device access'
+assert vllm.__version__=='0.24.0'
+assert metadata.version('numpy')=='2.2.6'
+assert metadata.version('torch')=='2.11.0+cu130'
+assert metadata.version('transformers')=='5.12.1'
+print(json.dumps({'event':'cpu_preflight_pass','versions':{name:metadata.version(name) for name in ['vllm','torch','transformers','numpy','soundfile','scipy','soxr','av']},'wav_roundtrip_shape':list(decoded.shape),'resampled_shape':list(resampled.shape),'feature_shape':list(features['input_features'].shape),'transcription_route_files':routes,'gpu_device_access':False}))
+
+# Validate only the installed CLI option declarations. Constructing the full vLLM
+# config on a no-GPU preflight host would try to infer a device.
+import argparse
+import ast
+import inspect
+from vllm.engine.arg_utils import AsyncEngineArgs
+parser = argparse.ArgumentParser()
+tree = ast.parse(Path(inspect.getfile(AsyncEngineArgs)).read_text())
+found = set()
+for node in ast.walk(tree):
+    if (isinstance(node, ast.Call) and isinstance(node.func, ast.Attribute)
+            and isinstance(node.func.value, ast.Name) and node.func.value.id == "parser"
+            and node.func.attr == "add_argument" and node.args
+            and isinstance(node.args[0], ast.Constant)
+            and node.args[0].value in {"--enable-log-requests", "--shutdown-timeout"}):
+        eval(compile(ast.Expression(node), "<installed-option-declaration>", "eval"),
+             {"parser": parser, "argparse": argparse, "AsyncEngineArgs": AsyncEngineArgs, "int": int})
+        found.add(node.args[0].value)
+assert len(found) == 2
+args = parser.parse_args(["--no-enable-log-requests", "--shutdown-timeout", "600"])
+assert args.enable_log_requests is False and args.shutdown_timeout == 600
+print("CLI_PRIVACY_AND_SHUTDOWN_DECLARATIONS_PASS")