mirror of
https://github.com/fawney19/Aether.git
synced 2026-09-02 17:30:23 +08:00
483d536e2c
- tiktoken 编码器改为 @lru_cache 全局缓存，避免多实例重复初始化 - 前缀匹配按长度排序，避免短前缀抢先匹配 - AuthService 更新 last_used_at 时临时关闭 expire_on_commit，减少额外 SELECT - UsageService.record_usage_batch 改用 bulk_insert_mappings 批量插入 - 已有记录查询增加 selectinload 预加载，避免 N+1 - Gemini normalizer 长行格式化 Co-Authored-By: AAEE86 <33052466+AAEE86@users.noreply.github.com>
42 lines
1.2 KiB
Python
42 lines
1.2 KiB
Python
import pytest
|
|
|
|
|
|
class _DummyEncoder:
|
|
def encode(self, text: str) -> list[int]:
|
|
return [0] * len(text)
|
|
|
|
|
|
class _DummyTiktoken:
|
|
def __init__(self, calls: dict[str, int]) -> None:
|
|
self._calls = calls
|
|
|
|
def get_encoding(self, _name: str) -> _DummyEncoder:
|
|
self._calls["get_encoding"] += 1
|
|
return _DummyEncoder()
|
|
|
|
def encoding_for_model(self, _model: str) -> _DummyEncoder:
|
|
self._calls["encoding_for_model"] += 1
|
|
return _DummyEncoder()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_encoder_is_globally_cached(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
import src.plugins.token.tiktoken_counter as tc
|
|
|
|
# 清理缓存，避免受其他测试影响
|
|
tc._get_encoder_cached.cache_clear()
|
|
|
|
calls = {"get_encoding": 0, "encoding_for_model": 0}
|
|
|
|
monkeypatch.setattr(tc, "TIKTOKEN_AVAILABLE", True)
|
|
monkeypatch.setattr(tc, "tiktoken", _DummyTiktoken(calls))
|
|
|
|
p1 = tc.TiktokenCounterPlugin()
|
|
p2 = tc.TiktokenCounterPlugin()
|
|
|
|
# 两个实例对同一 model 请求编码器，底层 get_encoding 应只触发一次
|
|
await p1.count_tokens("hi", model="gpt-4")
|
|
await p2.count_tokens("hi", model="gpt-4")
|
|
|
|
assert calls["get_encoding"] == 1
|