e4bf0710c7
数据库 - 新增迁移 0003：timeline_events.memory_source_id 外键 → memory_sources，便于按 ingest 源做时间线幂等 后端 - 记忆 - 新增 ingest 后 LLM 富化（摘要/事实/时间线），可配置开关与最大字符数 - 新增证据包组装：合并 chunk、摘要、事实、时间线、故事等检索结果；支持空 query 时是否仍带 rolling 等开关 - repo/retriever/service/router/schemas/summarizer/timeline/extractor 等扩展；文档 memory-retrieval.md 更新 后端 - 对话 WS - 增加 PING/PONG；分段 ASR 日志与空音频处理；转写失败与「无助手回复」错误提示更明确 - 助手多段回复持久化使用统一分隔符，与分段逻辑一致 后端 - Agent - reply_limits：按 [SPLIT] 与段落拆段，并保证非空 fallback，供 WS 与 TTS 多段下发 后端 - 回忆录任务 - transcript ingest 记录 source_id；任务成功结?
62 lines
1.8 KiB
Python
62 lines
1.8 KiB
Python
import asyncio
|
|
import sys
|
|
from types import SimpleNamespace
|
|
|
|
import pytest
|
|
|
|
from app.adapters.asr.whisper_local import (
|
|
WhisperASRProvider,
|
|
_looks_like_subtitle_hallucination,
|
|
)
|
|
|
|
|
|
def test_subtitle_watermark_detection() -> None:
|
|
assert _looks_like_subtitle_hallucination("字幕by索兰娅") is True
|
|
assert _looks_like_subtitle_hallucination("今天想聊聊童年往事") is False
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_transcribe_retries_decode_audio_after_discarded_pass2(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
class DummyModel:
|
|
def __init__(self) -> None:
|
|
self.calls: list[object] = []
|
|
|
|
def transcribe(self, audio: object, **_: object):
|
|
self.calls.append(audio)
|
|
n = len(self.calls)
|
|
if n == 1:
|
|
return iter([]), SimpleNamespace()
|
|
if n == 2:
|
|
return iter([SimpleNamespace(text="字幕by索兰娅")]), SimpleNamespace()
|
|
if n == 3:
|
|
assert audio == "decoded-audio"
|
|
return (
|
|
iter([SimpleNamespace(text="你好，今天想聊聊童年。")]),
|
|
SimpleNamespace(),
|
|
)
|
|
raise AssertionError(f"unexpected transcribe call #{n}")
|
|
|
|
async def fake_to_thread(fn):
|
|
return fn()
|
|
|
|
def fake_decode_audio(_: str, sampling_rate: int = 16000):
|
|
assert sampling_rate == 16000
|
|
return "decoded-audio"
|
|
|
|
monkeypatch.setattr(asyncio, "to_thread", fake_to_thread)
|
|
monkeypatch.setitem(
|
|
sys.modules,
|
|
"faster_whisper",
|
|
SimpleNamespace(decode_audio=fake_decode_audio),
|
|
)
|
|
|
|
provider = WhisperASRProvider()
|
|
provider._model = DummyModel()
|
|
|
|
text = await provider.transcribe(b"fake-audio", format="m4a")
|
|
|
|
assert text == "你好，今天想聊聊童年。"
|
|
assert len(provider._model.calls) == 3
|