81 lines
2.7 KiB
Python
81 lines
2.7 KiB
Python
|
"""Tests for the prompt-cache bootstrap script (mocked adapt/LLM)."""
|
||
|
|
|
||
|
|
import asyncio
|
||
|
|
import json
|
||
|
|
|
||
|
|
from pydantic import BaseModel
|
||
|
|
|
||
|
|
import scripts.build_judge_prompt_cache as builder
|
||
|
|
|
||
|
|
|
||
|
|
class _In(BaseModel):
|
||
|
|
question: str
|
||
|
|
|
||
|
|
|
||
|
|
class _Out(BaseModel):
|
||
|
|
statements: list[str]
|
||
|
|
|
||
|
|
|
||
|
|
class _FakeAdapted:
|
||
|
|
"""Fake adapted prompt returned by prompt.adapt()."""
|
||
|
|
|
||
|
|
def __init__(self):
|
||
|
|
self.instruction = "中文指令。"
|
||
|
|
self.language = "chinese"
|
||
|
|
self.examples = [(_In(question="问题"), _Out(statements=["陈述"]))]
|
||
|
|
|
||
|
|
|
||
|
|
class _FakePrompt:
|
||
|
|
"""Fake prompt with async adapt() that returns _FakeAdapted."""
|
||
|
|
|
||
|
|
def __init__(self):
|
||
|
|
self.input_model = _In
|
||
|
|
self.output_model = _Out
|
||
|
|
self.instruction = "English."
|
||
|
|
self.examples = [(_In(question="q"), _Out(statements=["s"]))]
|
||
|
|
self.language = "english"
|
||
|
|
|
||
|
|
async def adapt(self, target_language, llm, adapt_instruction=False):
|
||
|
|
assert target_language == "chinese"
|
||
|
|
assert adapt_instruction is True
|
||
|
|
return _FakeAdapted()
|
||
|
|
|
||
|
|
|
||
|
|
def test_serialize_prompt_shape():
|
||
|
|
"""serialize_prompt emits the expected committed cache schema."""
|
||
|
|
data = builder.serialize_prompt(
|
||
|
|
_FakeAdapted(), "hash123", "context_recall", "prompt", "zh", "0.4.3"
|
||
|
|
)
|
||
|
|
assert data["metric"] == "context_recall"
|
||
|
|
assert data["prompt_attr"] == "prompt"
|
||
|
|
assert data["language"] == "chinese"
|
||
|
|
assert data["source_hash"] == "hash123"
|
||
|
|
assert data["instruction"] == "中文指令。"
|
||
|
|
assert data["examples"] == [
|
||
|
|
{"input": {"question": "问题"}, "output": {"statements": ["陈述"]}}
|
||
|
|
]
|
||
|
|
|
||
|
|
|
||
|
|
def test_build_cache_writes_all_files(tmp_path, monkeypatch):
|
||
|
|
"""build_cache writes one JSON per (metric, attr) under CACHE_ROOT/<language>/."""
|
||
|
|
# Build a fake registry where every prompt attr is a _FakePrompt.
|
||
|
|
fake_registry = {name: type("M", (), {})() for name in builder.METRIC_PROMPT_ATTRS}
|
||
|
|
for name, attrs in builder.METRIC_PROMPT_ATTRS.items():
|
||
|
|
for attr in attrs:
|
||
|
|
setattr(fake_registry[name], attr, _FakePrompt())
|
||
|
|
|
||
|
|
monkeypatch.setattr(builder, "build_models", lambda j, e, s: (object(), object()))
|
||
|
|
monkeypatch.setattr(builder, "build_metric_registry", lambda llm, emb: fake_registry)
|
||
|
|
monkeypatch.setattr(builder, "CACHE_ROOT", tmp_path)
|
||
|
|
|
||
|
|
written = asyncio.run(builder.build_cache("zh", "gpt-5", "emb", object()))
|
||
|
|
|
||
|
|
expected_count = sum(len(a) for a in builder.METRIC_PROMPT_ATTRS.values())
|
||
|
|
assert len(written) == expected_count
|
||
|
|
|
||
|
|
sample = tmp_path / "zh" / "context_recall__prompt.json"
|
||
|
|
assert sample.exists()
|
||
|
|
data = json.loads(sample.read_text(encoding="utf-8"))
|
||
|
|
assert data["instruction"] == "中文指令。"
|
||
|
|
assert data["metric"] == "context_recall"
|