feat(dictate): support configurable ASR backends

This commit is contained in:
jb
2026-09-03 00:08:00 -04:00
parent 67877297d0
commit 2c3ee1f014
40 changed files with 7055 additions and 489 deletions
+552 -2
View File
@@ -1,11 +1,22 @@
from concurrent.futures import Future
from collections.abc import Sequence
from dataclasses import dataclass
import errno
import selectors
import subprocess
import sys
import unittest
from unittest.mock import patch
from pi_dictate_service.protocol import MAX_TRANSCRIPT_BYTES, PROTOCOL_VERSION, parse_request
from pi_dictate_service.protocol import (
MAX_FRAME_BYTES,
MAX_TRANSCRIPT_BYTES,
PROTOCOL_VERSION,
encode_frame,
parse_request,
)
from pi_dictate_service.recorder import Capture, RecorderError
from pi_dictate_service.server import DictateServiceCore, Outbound
from pi_dictate_service.server import DictateServiceCore, Outbound, serve
class Clock:
@@ -93,6 +104,154 @@ class FakeRecorder:
return failure
class SpawnFailRecorder(FakeRecorder):
cleanup_complete = True
def start(self) -> None:
raise RecorderError("recorder_spawn", "could not start pw-record")
class SpawnFailRecorderFactory:
def __call__(self) -> SpawnFailRecorder:
return SpawnFailRecorder()
class DelayedCleanupRecorder(FakeRecorder):
def __init__(self) -> None:
super().__init__()
self.cleanup_complete = False
self.cleanup_attempts = 0
self.cleanup_started = False
def stop(self) -> Capture:
self.cleanup_started = True
raise RecorderError("recorder_timeout", "pw-record cleanup did not complete")
def poll_unexpected(self) -> RecorderError | None:
if not self.cleanup_started:
return None
self.cleanup_attempts += 1
if self.cleanup_attempts >= 3:
self.cleanup_complete = True
return None
class DelayedCleanupRecorderFactory:
def __init__(self) -> None:
self.instance = DelayedCleanupRecorder()
def __call__(self) -> DelayedCleanupRecorder:
return self.instance
class DelayedCloseTurn:
sample_rate_hz = 16_000
retain_pcm = True
def __init__(self) -> None:
self.close_calls = 0
@property
def cleanup_complete(self) -> bool:
return self.close_calls >= 3
def enqueue_pcm(self, chunk: bytes) -> None:
return None
def finish(self, capture: Capture | None = None) -> str:
return "cloud result"
def poll_error(self) -> None:
return None
def cancel(self) -> None:
return None
def close(self) -> None:
self.close_calls += 1
class StreamingTurn:
sample_rate_hz = 24_000
retain_pcm = False
def __init__(self, events: list[str]) -> None:
self.events = events
self.closed = False
@property
def cleanup_complete(self) -> bool:
return self.closed
def enqueue_pcm(self, chunk: bytes) -> None:
self.events.append(f"audio-{chunk.decode('ascii')}")
def finish(self, capture: Capture | None = None) -> str:
self.events.append("finish")
self.assert_capture = capture
return "cloud result"
def poll_error(self) -> None:
return None
def cancel(self) -> None:
self.events.append("cancel")
def close(self) -> None:
self.closed = True
class StreamingRecorder(FakeRecorder):
def __init__(self, sink: StreamingTurn, events: list[str]) -> None:
super().__init__()
self.sink = sink
self.events = events
self.capture = Capture(b"", -15, 15, b"")
def start(self) -> None:
super().start()
self.sink.enqueue_pcm(b"a")
self.sink.enqueue_pcm(b"b")
def stop(self) -> Capture:
self.events.append("recorder-stop")
return super().stop()
class StreamingRecorderFactory:
def __init__(self, events: list[str]) -> None:
self.events = events
self.sample_rate_hz: int | None = None
self.instance: StreamingRecorder | None = None
def __call__(
self,
*,
sample_rate_hz: int,
pcm_sink: StreamingTurn,
retain_pcm: bool,
) -> StreamingRecorder:
self.sample_rate_hz = sample_rate_hz
if retain_pcm:
raise AssertionError("cloud capture must not retain PCM")
self.instance = StreamingRecorder(pcm_sink, self.events)
return self.instance
class FakeBackend:
sample_rate_hz = 16_000
descriptor = type("Descriptor", (), {"backend": "fake", "model": "fake-model"})()
def __init__(self, turn: DelayedCloseTurn | StreamingTurn) -> None:
self.turn = turn
def start_turn(self) -> DelayedCloseTurn:
return self.turn
def cancel_prepare(self) -> None:
return None
class RecorderFactory:
def __init__(self) -> None:
self.instances: list[FakeRecorder] = []
@@ -271,6 +430,121 @@ class StopAndInferenceTests(CoreTestCase):
self.assertEqual(completed[0]["transcript"], "dictated text")
self.assertEqual(completed[1]["state"], "idle")
def test_realtime_backend_streams_ordered_pcm_and_finalizes_after_recorder_stop(self) -> None:
events: list[str] = []
turn = StreamingTurn(events)
recorders = StreamingRecorderFactory(events)
core = DictateServiceCore(
backend=FakeBackend(turn),
recorder_factory=recorders,
executor=self.executor,
clock=self.clock,
idle_seconds=900,
)
core.accepted("a")
core.handle_request("a", parse_request({"version": 2, "type": "hello", "requestId": "hello"}))
core.drain_events()
core.handle_request("a", parse_request({
"version": 2,
"type": "start",
"requestId": "start",
"generationId": "g1",
}))
self.executor.run_next()
core.poll()
self.assertEqual(recorders.sample_rate_hz, 24_000)
self.assertEqual(events, ["audio-a", "audio-b"])
core.drain_events()
core.handle_request("a", parse_request({
"version": 2,
"type": "stop",
"requestId": "stop",
"generationId": "g1",
}))
self.executor.run_next()
core.poll()
self.executor.run_next()
core.poll()
self.assertEqual(events, ["audio-a", "audio-b", "recorder-stop", "finish"])
result = [event.frame for event in core.drain_events() if event.frame["type"] == "result"]
self.assertEqual(result[0]["transcript"], "cloud result")
self.assertIsNone(core.active_generation_id)
def test_cancel_after_prepare_completion_tracks_turn_cleanup_before_release(self) -> None:
events: list[str] = []
turn = StreamingTurn(events)
core = DictateServiceCore(
backend=FakeBackend(turn),
recorder_factory=StreamingRecorderFactory(events),
executor=self.executor,
clock=self.clock,
idle_seconds=900,
)
core.accepted("a")
core.handle_request("a", parse_request({"version": 2, "type": "hello", "requestId": "hello"}))
core.drain_events()
core.handle_request("a", parse_request({
"version": 2,
"type": "start",
"requestId": "start",
"generationId": "g1",
}))
self.executor.run_next()
# The future has completed, but the socket loop has not yet applied it.
core.handle_request("a", parse_request({
"version": 2,
"type": "cancel",
"requestId": "cancel",
"generationId": "g1",
}))
core.poll()
self.assertIn("cancel", events)
self.assertTrue(turn.cleanup_complete)
self.assertIsNone(core.active_generation_id)
def test_completed_turn_retries_bounded_cleanup_before_releasing_generation(self) -> None:
turn = DelayedCloseTurn()
core = DictateServiceCore(
backend=FakeBackend(turn),
recorder_factory=self.recorders,
executor=self.executor,
clock=self.clock,
idle_seconds=900,
)
core.accepted("a")
core.handle_request("a", parse_request({"version": 2, "type": "hello", "requestId": "hello"}))
core.drain_events()
core.handle_request("a", parse_request({
"version": 2,
"type": "start",
"requestId": "start",
"generationId": "g1",
}))
self.executor.run_next()
core.poll()
core.drain_events()
core.handle_request("a", parse_request({
"version": 2,
"type": "stop",
"requestId": "stop",
"generationId": "g1",
}))
self.executor.run_next()
core.poll()
self.executor.run_next()
core.poll()
self.assertEqual(core.active_generation_id, "g1")
self.assertEqual(turn.close_calls, 2)
core.poll()
self.assertIsNone(core.active_generation_id)
self.assertEqual(turn.close_calls, 3)
def test_empty_transcript_is_a_result(self) -> None:
self.model.transcript = ""
self.load_to_listening()
@@ -321,6 +595,8 @@ class StopAndInferenceTests(CoreTestCase):
recorder = self.load_to_listening()
recorder.unexpected = RecorderError("recorder_exit", "pw-record exited with code 3")
self.core.poll()
self.executor.run_next()
self.core.poll()
failed = self.frames(self.core.drain_events(), "a")
@@ -332,12 +608,286 @@ class StopAndInferenceTests(CoreTestCase):
recorder.unexpected = RecorderError("recorder_exit", "pw-record exited with code 0")
failed = self.request("a", "stop", "stop", "g1")
self.executor.run_next()
self.core.poll()
failed.extend(self.frames(self.core.drain_events(), "a"))
self.assertEqual(failed[0]["code"], "recorder_exit")
self.assertEqual(failed[-1]["state"], "idle")
self.assertEqual(self.executor.pending, [])
def test_recorder_spawn_failure_releases_generation_without_cleanup_loop(self) -> None:
core = DictateServiceCore(
model=self.model,
recorder_factory=SpawnFailRecorderFactory(),
executor=self.executor,
clock=self.clock,
idle_seconds=900,
)
core.accepted("a")
core.handle_request("a", parse_request({
"version": 2, "type": "hello", "requestId": "hello"
}))
core.drain_events()
core.handle_request("a", parse_request({
"version": 2,
"type": "start",
"requestId": "start",
"generationId": "g1",
}))
self.executor.run_next()
core.poll()
events = self.frames(core.drain_events(), "a")
self.assertEqual(events[-2]["code"], "recorder_spawn")
self.assertEqual(events[-1]["state"], "idle")
self.assertIsNone(core.active_generation_id)
self.assertEqual(self.executor.pending, [])
def test_unreaped_recorder_keeps_generation_busy_until_cleanup_completes(self) -> None:
recorders = DelayedCleanupRecorderFactory()
core = DictateServiceCore(
model=self.model,
recorder_factory=recorders,
executor=self.executor,
clock=self.clock,
idle_seconds=900,
)
core.accepted("a")
core.handle_request("a", parse_request({
"version": 2, "type": "hello", "requestId": "hello"
}))
core.drain_events()
core.handle_request("a", parse_request({
"version": 2,
"type": "start",
"requestId": "start",
"generationId": "g1",
}))
self.executor.run_next()
core.poll()
core.drain_events()
core.handle_request("a", parse_request({
"version": 2,
"type": "stop",
"requestId": "stop",
"generationId": "g1",
}))
self.executor.run_next()
core.poll()
self.assertEqual(core.active_generation_id, "g1")
# First reap the cancellation worker scheduled by the terminal stop.
self.executor.run_next()
core.poll()
for attempt in range(1, 4):
self.executor.run_next()
core.poll()
if attempt < 3:
self.assertEqual(core.active_generation_id, "g1")
self.assertIsNone(core.active_generation_id)
self.assertEqual(recorders.instance.cleanup_attempts, 3)
class SocketLoopRegressionTests(unittest.TestCase):
def test_output_overflow_does_not_use_the_closed_socket_from_same_selector_event(self) -> None:
frame = {"padding": "x" * (MAX_FRAME_BYTES - len(encode_frame({"padding": ""})))}
self.assertEqual(len(encode_frame(frame)), MAX_FRAME_BYTES)
client = _FakeClientSocket()
listener = _FakeListener(client)
selector = _FakeSelector(client)
core = _FakeLoopCore(
Outbound("client-1", frame),
)
with patch("pi_dictate_service.server.selectors.DefaultSelector", return_value=selector):
serve(listener, core)
self.assertEqual(client.send_calls, 0)
self.assertTrue(client.closed)
self.assertTrue(listener.closed)
def test_close_does_not_wait_for_owned_executor_workers(self) -> None:
executor = _ShutdownRecordingExecutor()
with patch("pi_dictate_service.server._DaemonExecutor", return_value=executor):
core = DictateServiceCore(model=FakeModel())
core.accepted("a")
core.handle_request(
"a", parse_request({"version": PROTOCOL_VERSION, "type": "hello", "requestId": "h"})
)
core.drain_events()
core.handle_request(
"a",
parse_request(
{
"version": PROTOCOL_VERSION,
"type": "start",
"requestId": "s",
"generationId": "g",
}
),
)
core.close()
self.assertEqual(executor.shutdown_args, (False, True))
def test_real_owned_executor_does_not_block_interpreter_exit(self) -> None:
program = """
import threading
import time
from pi_dictate_service.protocol import parse_request
from pi_dictate_service.server import DictateServiceCore
class StuckModel:
loaded = False
def load(self):
threading.Event().wait()
def transcribe(self, _samples):
return ''
core = DictateServiceCore(model=StuckModel())
core.accepted('a')
core.handle_request('a', parse_request({'version': 2, 'type': 'hello', 'requestId': 'h'}))
core.drain_events()
core.handle_request('a', parse_request({
'version': 2, 'type': 'start', 'requestId': 's', 'generationId': 'g'
}))
time.sleep(0.05)
core.close()
print('closed')
"""
result = subprocess.run(
[sys.executable, "-c", program],
text=True,
capture_output=True,
timeout=2,
check=False,
)
self.assertEqual(result.returncode, 0, result.stderr)
self.assertEqual(result.stdout.strip(), "closed")
@dataclass
class _FakeSelectorKey:
data: str | None
class _FakeSelector:
def __init__(self, client: "_FakeClientSocket") -> None:
self._events = [
[(_FakeSelectorKey(None), selectors.EVENT_READ)],
[(_FakeSelectorKey("client-1"), selectors.EVENT_READ | selectors.EVENT_WRITE)],
]
self.client = client
self.unregistered: list[object] = []
self.closed = False
def register(self, fileobj: object, _events: int, _data: object = None) -> None:
return None
def unregister(self, fileobj: object) -> None:
self.unregistered.append(fileobj)
def modify(self, fileobj: object, _events: int, _data: object = None) -> None:
if fileobj is self.client and self.client.closed:
raise OSError(errno.EBADF, "bad file descriptor")
def select(self, timeout: float | None = None) -> list[tuple[_FakeSelectorKey, int]]:
return self._events.pop(0)
def close(self) -> None:
self.closed = True
class _FakeClientSocket:
def __init__(self) -> None:
self.closed = False
self.send_calls = 0
self._read = True
def setblocking(self, _value: bool) -> None:
return None
def recv(self, _size: int) -> bytes:
if self._read:
self._read = False
return b"{broken}\n"
return b""
def send(self, _data: bytearray) -> int:
self.send_calls += 1
raise OSError(errno.EBADF, "bad file descriptor")
def close(self) -> None:
self.closed = True
class _FakeListener:
def __init__(self, client: _FakeClientSocket) -> None:
self.client = client
self.closed = False
self._accepted = False
def setblocking(self, _value: bool) -> None:
return None
def accept(self) -> tuple[_FakeClientSocket, object]:
if self._accepted:
raise BlockingIOError
self._accepted = True
return self.client, None
def close(self) -> None:
self.closed = True
class _FakeLoopCore:
def __init__(self, outbound: Outbound) -> None:
self.outbound = outbound
self.accepted_client: str | None = None
self._outbound_sent = False
self._exit_checks = 0
def should_exit(self) -> bool:
self._exit_checks += 1
return self._exit_checks >= 3
def poll(self) -> None:
return None
def drain_events(self) -> list[Outbound]:
if self.accepted_client is not None and not self._outbound_sent:
self._outbound_sent = True
return [self.outbound]
return []
def accepted(self, client_id: str) -> None:
self.accepted_client = client_id
def disconnect(self, _client_id: str) -> None:
return None
def close(self) -> None:
return None
class _ShutdownRecordingExecutor:
def __init__(self) -> None:
self.shutdown_args: tuple[bool, bool] | None = None
def submit(self, _function: object, *_args: object) -> Future[object]:
return Future()
def shutdown(self, *, wait: bool = True, cancel_futures: bool = False) -> None:
self.shutdown_args = (wait, cancel_futures)
if wait:
raise AssertionError("shutdown waited for a hung worker")
class IdleTests(CoreTestCase):
def test_only_valid_requests_reset_idle_and_workers_suspend_then_restart_timer(self) -> None:
self.core.accepted("a")