mirror of
https://github.com/AstrBotDevs/AstrBot
synced 2026-07-01 01:10:21 +08:00
7c366a708b
* fix: unify media reference handling * fix: accept bare base64 record media refs * chore: update agents.md * fix: unify file URI handling across media components and utilities * fix: unify media reference type handling with MediaRefStr alias * Potential fix for pull request finding 'CodeQL / Incomplete URL substring sanitization' Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com> * Update astrbot/core/platform/sources/discord/discord_platform_adapter.py Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * fix: unify media handling and improve base64 decoding across components * fix: simplify client_kwargs type definition and enhance media message handling in platform adapter * fix: unify media utility documentation and enhance function descriptions * perf: drop "pilk" requirement, improve audio outbound for tencent-related IM apps which using silk * fix: unify Tencent Silk audio handling and enhance media resolver functionality --- - Centralize media reference materialization and base64 resolution for local paths, http(s), base64://, data URIs, and legacy bare base64 payloads. - Normalize incoming Record audio to wav and Image media to temporary jpg during preprocess, with event-scoped cleanup. - Reuse the shared media resolver across OpenAI, Gemini, Anthropic, MiMo, DeerFlow, STT, and platform media paths while sanitizing logs and cleaning temporary conversion outputs. - Ensure generated TTS audio is tracked for cleanup after the event finishes. fix #8676 fix #8543 fix #7588 fix #7580 fix #8030 fix #8034 fix #7461 fix #7565 fix #6509 fix #7144 fix #7795 --------- Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
76 lines
2.3 KiB
Python
76 lines
2.3 KiB
Python
from pathlib import Path
|
|
from types import SimpleNamespace
|
|
from unittest.mock import AsyncMock
|
|
|
|
import pytest
|
|
|
|
from astrbot.core.provider.sources.whisper_api_source import ProviderOpenAIWhisperAPI
|
|
|
|
|
|
def _make_provider() -> ProviderOpenAIWhisperAPI:
|
|
provider = ProviderOpenAIWhisperAPI(
|
|
provider_config={
|
|
"id": "test-whisper-api",
|
|
"type": "openai_whisper_api",
|
|
"model": "whisper-1",
|
|
"api_key": "test-key",
|
|
},
|
|
provider_settings={},
|
|
)
|
|
provider.client = SimpleNamespace(
|
|
audio=SimpleNamespace(
|
|
transcriptions=SimpleNamespace(
|
|
create=AsyncMock(return_value=SimpleNamespace(text="transcribed text"))
|
|
)
|
|
),
|
|
close=AsyncMock(),
|
|
)
|
|
return provider
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_get_text_converts_opus_files_to_wav_before_transcription(
|
|
tmp_path: Path, monkeypatch: pytest.MonkeyPatch
|
|
):
|
|
provider = _make_provider()
|
|
opus_path = tmp_path / "voice.opus"
|
|
opus_path.write_bytes(b"fake opus data")
|
|
|
|
conversions: list[tuple[str, str]] = []
|
|
|
|
async def fake_convert_audio_to_wav(
|
|
audio_path: str, output_path: str | None = None
|
|
):
|
|
if output_path is None:
|
|
output_path = str(tmp_path / "converted.wav")
|
|
conversions.append((audio_path, output_path))
|
|
Path(output_path).write_bytes(b"fake wav data")
|
|
return output_path
|
|
|
|
monkeypatch.setattr(
|
|
"astrbot.core.utils.media_utils.get_astrbot_temp_path",
|
|
lambda: str(tmp_path),
|
|
)
|
|
monkeypatch.setattr(
|
|
"astrbot.core.utils.media_utils.convert_audio_to_wav",
|
|
fake_convert_audio_to_wav,
|
|
)
|
|
|
|
try:
|
|
result = await provider.get_text(str(opus_path))
|
|
|
|
assert result == "transcribed text"
|
|
assert conversions and conversions[0][0] == str(opus_path)
|
|
converted_path = Path(conversions[0][1])
|
|
assert converted_path.suffix == ".wav"
|
|
assert not converted_path.exists()
|
|
|
|
create_mock = provider.client.audio.transcriptions.create
|
|
create_mock.assert_awaited_once()
|
|
file_arg = create_mock.await_args.kwargs["file"]
|
|
assert file_arg[0] == "audio.wav"
|
|
assert file_arg[1].name.endswith(".wav")
|
|
file_arg[1].close()
|
|
finally:
|
|
await provider.terminate()
|