feat(dictate): support configurable ASR backends

services/dictate/src/pi_dictate_service/live_smoke.py

@@ -0,0 +1,69 @@
+"""Opt-in live cloud contract smoke test using a short raw PCM fixture."""
+
+from __future__ import annotations
+
+import argparse
+import os
+from pathlib import Path
+import stat
+
+from .backend import backend_from_config
+from .config import load_config
+
+MAX_SAMPLE_BYTES = 240_000  # five seconds of 24 kHz mono PCM16
+CHUNK_BYTES = 4_800
+
+
+def _read_sample(path: Path) -> bytes:
+    descriptor = os.open(
+        path,
+        os.O_RDONLY | getattr(os, "O_CLOEXEC", 0) | getattr(os, "O_NOFOLLOW", 0),
+    )
+    try:
+        info = os.fstat(descriptor)
+        if not stat.S_ISREG(info.st_mode):
+            raise ValueError("sample must be a regular file")
+        if not 0 < info.st_size <= MAX_SAMPLE_BYTES or info.st_size % 2:
+            raise ValueError("sample must contain at most five seconds of even-length PCM16")
+        sample = bytearray()
+        while len(sample) <= MAX_SAMPLE_BYTES:
+            chunk = os.read(descriptor, min(64 * 1024, MAX_SAMPLE_BYTES + 1 - len(sample)))
+            if not chunk:
+                break
+            sample.extend(chunk)
+        if len(sample) != info.st_size:
+            raise ValueError("sample changed while it was being read")
+        return bytes(sample)
+    finally:
+        os.close(descriptor)
+
+
+def main() -> None:
+    parser = argparse.ArgumentParser(
+        description="Send one non-sensitive 24 kHz mono PCM16 sample to the configured cloud backend."
+    )
+    parser.add_argument("sample", type=Path, help="raw 24 kHz mono signed-16 little-endian PCM")
+    parser.add_argument(
+        "--config",
+        type=Path,
+        default=Path("~/.config/pi-dictate/config.json").expanduser(),
+    )
+    arguments = parser.parse_args()
+
+    config = load_config(arguments.config)
+    if config.backend not in {"meta", "openai"}:
+        parser.error("the configured backend must be meta or openai")
+    backend = backend_from_config(config)
+    sample = _read_sample(arguments.sample)
+    turn = backend.start_turn()
+    try:
+        for offset in range(0, len(sample), CHUNK_BYTES):
+            turn.enqueue_pcm(sample[offset : offset + CHUNK_BYTES])
+        transcript = turn.finish()
+    finally:
+        turn.close()
+    print(f"{backend.descriptor.backend}/{backend.descriptor.model}: {transcript!r}")
+
+
+if __name__ == "__main__":
+    main()