Files
姚章浩 693cd952cd feat(asset): 清理被截断的结尾图片引用,修复整单 502
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
2026-09-16 10:01:27 +08:00

114 lines
3.7 KiB
Python

from uuid import UUID
import httpx
import pytest
from pydantic import SecretStr
from knowledge_adapter.weknora_client import (
WeKnoraBadResponseError,
WeKnoraClient,
WeKnoraUnavailableError,
)
KB_ID = UUID("3904b40e-278b-4273-a6fa-db6cbc975587")
WEKNORA_KEY = "test-weknora-key"
async def test_search_uses_only_readonly_endpoint_and_expected_contract() -> None:
requests: list[httpx.Request] = []
def handler(request: httpx.Request) -> httpx.Response:
requests.append(request)
return httpx.Response(200, json={"success": True, "data": []})
client = WeKnoraClient(
base_url="http://weknora.internal:8080",
api_key=SecretStr(WEKNORA_KEY),
timeout_seconds=15,
transport=httpx.MockTransport(handler),
)
async with client:
results = await client.search(query="normalized query", knowledge_base_id=KB_ID)
assert results == []
assert len(requests) == 1
request = requests[0]
assert request.method == "POST"
assert request.url.path == "/api/v1/knowledge-search"
assert request.headers["X-API-Key"] == WEKNORA_KEY
assert request.headers.get("Authorization") is None
assert request.read().decode() == (
'{"query":"normalized query",'
'"knowledge_base_ids":["3904b40e-278b-4273-a6fa-db6cbc975587"]}'
)
async def test_timeout_becomes_sanitized_unavailable_error() -> None:
def handler(request: httpx.Request) -> httpx.Response:
raise httpx.ReadTimeout("internal timeout details", request=request)
client = WeKnoraClient(
base_url="http://weknora.internal:8080",
api_key=SecretStr(WEKNORA_KEY),
timeout_seconds=15,
transport=httpx.MockTransport(handler),
)
with pytest.raises(WeKnoraUnavailableError) as captured:
async with client:
await client.search(query="sensitive query", knowledge_base_id=KB_ID)
assert str(captured.value) == "WeKnora unavailable"
async def test_500_becomes_sanitized_bad_response_error() -> None:
def handler(_request: httpx.Request) -> httpx.Response:
return httpx.Response(500, text="sensitive upstream failure")
client = WeKnoraClient(
base_url="http://weknora.internal:8080",
api_key=SecretStr(WEKNORA_KEY),
timeout_seconds=15,
transport=httpx.MockTransport(handler),
)
with pytest.raises(WeKnoraBadResponseError) as captured:
async with client:
await client.search(query="sensitive query", knowledge_base_id=KB_ID)
assert str(captured.value) == "invalid WeKnora response"
async def test_non_json_200_becomes_sanitized_bad_response_error() -> None:
def handler(_request: httpx.Request) -> httpx.Response:
return httpx.Response(200, text="not-json sensitive body")
client = WeKnoraClient(
base_url="http://weknora.internal:8080",
api_key=SecretStr(WEKNORA_KEY),
timeout_seconds=15,
transport=httpx.MockTransport(handler),
)
with pytest.raises(WeKnoraBadResponseError) as captured:
async with client:
await client.search(query="sensitive query", knowledge_base_id=KB_ID)
assert str(captured.value) == "invalid WeKnora response"
async def test_success_false_becomes_bad_response_error() -> None:
def handler(_request: httpx.Request) -> httpx.Response:
return httpx.Response(200, json={"success": False, "data": []})
client = WeKnoraClient(
base_url="http://weknora.internal:8080",
api_key=SecretStr(WEKNORA_KEY),
timeout_seconds=15,
transport=httpx.MockTransport(handler),
)
with pytest.raises(WeKnoraBadResponseError):
async with client:
await client.search(query="query", knowledge_base_id=KB_ID)