The pre-fix wrapper at stacks/ace-step/infer-api.py returned a JSON
{output_path: "..."} reference to a file written inside the
container at /app/outputs/. That path was unreachable from outside
the container — every consumer got 134 bytes of JSON-pretending-to-
be-WAV instead of audio. Surfaced by the asset_engine consumer's
end-to-end smoke (althing thread 01KRCJF7NGMXYE9F62Q1A6KFD4 msg 5);
my own earlier smoke missed it because I checked HTTP=200 and stopped
reading instead of inspecting the response body.
Wrapper now reads back the file the pipeline writes and streams the
bytes via fastapi.responses.Response with media_type set from the
audio_format request field (audio/wav | audio/mpeg | audio/flac).
The in-container path is exposed via X-Output-Path header for log
correlation but is no longer load-bearing.
Verified end-to-end against live ace-step on irv-ml1:
POST /generate -> HTTP 200 in 80s
content-type: audio/wav
content-length: 945226
x-output-path: /app/outputs/output_cfe87d1d....wav
$ file response.wav
RIFF (little-endian) data, WAVE audio, Microsoft PCM, 16 bit,
stereo 48000 Hz
Catalog: ace-step bumped version 3 -> 4. Dropped
response.output_field (no longer applicable). reproducibility.notes
expanded to record both the v2 18-arg-tuple fix and this v4
inline-streaming change so the history is auditable from the
catalog itself.
Stale ACEStepOutput Pydantic model left in infer-api.py for now —
unused but small; future cleanup.
Three upstream gaps surfaced once /generate was actually exercised:
1. infer-api.py builds an 18-arg positional tuple but the pipeline
expects 24 — first missing arg is `format`, so audio_duration
shifts into format's slot and the pipeline calls len() on an
int. Ship a patched copy of infer-api.py and COPY over upstream's
in the Dockerfile. Also handle empty lora_name_or_path -> "none"
(empty string trips HF Hub's repo-id validator).
2. torchcodec + ffmpeg are required by the WAV save path but neither
is in upstream requirements.txt. Without them every /generate
runs to completion and then 500s at write-time.
3. ACE-Step caches checkpoints at /root/.cache/ace-step/checkpoints
(HARDCODED, not honored by HF_HOME). Mount our persistent dir
there so the ~7 GB model survives container recreates.
Bench on A6000 (cached model, lo-fi hip hop, 60-step euler/apg):
10s @ 27 steps -> 9.4s (0.94x)
30s @ 60 steps -> 11.2s (0.37x, ~2.7x realtime)
60s @ 60 steps -> 14.8s (0.24x, ~4x realtime)
vh