姚章浩
693cd952cd
仓库首次入库（此前仅存在于本地工作区与测试服构建产物中，未上传）。 改动（src/knowledge_adapter/asset_content_processor.py）： - 新增 _TRUNCATED_TRAILING_MARKDOWN_RESOURCE_IMAGE 规则，清除 chunk 末尾被截断的 ![](resource://xxxx 残片（WeKnora 分块在图片引用中间截断时产生，旧逻辑无法匹配完整引用， 残留 resource:// 触发 ContentProcessingError，导致整单 502） - 回归测试 tests/test_asset_content_processor.py:: test_truncated_trailing_markdown_resource_image_is_removed 验证证据： - 测试服 120.76.217.51，镜像 knowledge-adapter-service:reviewed-test-aeab4b5fca2d （release aeab4b5fca2d8661）：KB d015d05c-25c8-4d63-b2ab-e8590d3c2dfb 5 个查询全部 http=200、records=5、残留 resource:// = 0；KB b9dacd62 无退化；容器日志无 error/exception - 本地：pytest 141 项全通过、ruff 全通过 - 该文件与 258c31e0fe07fd08 源码的差异经逐文件 md5 比对，为唯一变更文件
92 lines
2.6 KiB
Python
92 lines
2.6 KiB
Python
import hashlib
|
|
import hmac
|
|
from collections.abc import AsyncIterator
|
|
|
|
import httpx
|
|
import pytest
|
|
|
|
from knowledge_adapter.app import create_app
|
|
from knowledge_adapter.auth import DifyKeyAuthenticator
|
|
|
|
CURRENT_KEY = "c" * 32
|
|
NEXT_KEY = "n" * 32
|
|
VALID_PAYLOAD = {
|
|
"knowledge_id": "3904b40e-278b-4273-a6fa-db6cbc975587",
|
|
"query": "test query",
|
|
"retrieval_setting": {"top_k": 3, "score_threshold": 0.5},
|
|
}
|
|
|
|
|
|
def sha256_hex(value: str) -> str:
|
|
return hashlib.sha256(value.encode()).hexdigest()
|
|
|
|
|
|
@pytest.fixture
|
|
async def client() -> AsyncIterator[httpx.AsyncClient]:
|
|
authenticator = DifyKeyAuthenticator(
|
|
current_hash=sha256_hex(CURRENT_KEY),
|
|
next_hash=sha256_hex(NEXT_KEY),
|
|
)
|
|
transport = httpx.ASGITransport(app=create_app(authenticator=authenticator))
|
|
async with httpx.AsyncClient(transport=transport, base_url="http://test") as value:
|
|
yield value
|
|
|
|
|
|
async def test_retrieval_without_bearer_key_returns_401(client: httpx.AsyncClient) -> None:
|
|
response = await client.post("/retrieval", json=VALID_PAYLOAD)
|
|
|
|
assert response.status_code == 401
|
|
|
|
|
|
async def test_retrieval_with_wrong_bearer_key_returns_401(client: httpx.AsyncClient) -> None:
|
|
response = await client.post(
|
|
"/retrieval",
|
|
headers={"Authorization": f"Bearer {'x' * 32}"},
|
|
json=VALID_PAYLOAD,
|
|
)
|
|
|
|
assert response.status_code == 401
|
|
|
|
|
|
async def test_retrieval_with_current_key_returns_200(client: httpx.AsyncClient) -> None:
|
|
response = await client.post(
|
|
"/retrieval",
|
|
headers={"Authorization": f"Bearer {CURRENT_KEY}"},
|
|
json=VALID_PAYLOAD,
|
|
)
|
|
|
|
assert response.status_code == 200
|
|
|
|
|
|
async def test_retrieval_with_next_key_returns_200(client: httpx.AsyncClient) -> None:
|
|
response = await client.post(
|
|
"/retrieval",
|
|
headers={"Authorization": f"Bearer {NEXT_KEY}"},
|
|
json=VALID_PAYLOAD,
|
|
)
|
|
|
|
assert response.status_code == 200
|
|
|
|
|
|
async def test_current_match_does_not_short_circuit_next_hash_comparison(
|
|
client: httpx.AsyncClient,
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
original_compare = hmac.compare_digest
|
|
compared_hashes: list[str] = []
|
|
|
|
def recording_compare(digest: str, configured_hash: str) -> bool:
|
|
compared_hashes.append(configured_hash)
|
|
return original_compare(digest, configured_hash)
|
|
|
|
monkeypatch.setattr("knowledge_adapter.auth.hmac.compare_digest", recording_compare)
|
|
|
|
response = await client.post(
|
|
"/retrieval",
|
|
headers={"Authorization": f"Bearer {CURRENT_KEY}"},
|
|
json=VALID_PAYLOAD,
|
|
)
|
|
|
|
assert response.status_code == 200
|
|
assert len(compared_hashes) == 2
|