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

90 lines
2.8 KiB
Python

from types import TracebackType
from uuid import UUID
import httpx
from pydantic import SecretStr
from knowledge_adapter.observability import current_request_id
class WeKnoraUnavailableError(Exception):
"""WeKnora could not be reached within the configured budget."""
class WeKnoraBadResponseError(Exception):
"""WeKnora returned an unusable response."""
class WeKnoraClient:
def __init__(
self,
*,
base_url: str,
api_key: SecretStr,
timeout_seconds: float,
transport: httpx.AsyncBaseTransport | None = None,
) -> None:
short_timeout = min(5.0, timeout_seconds)
timeout = httpx.Timeout(
timeout_seconds,
connect=short_timeout,
read=timeout_seconds,
write=short_timeout,
pool=short_timeout,
)
limits = httpx.Limits(max_connections=100, max_keepalive_connections=20)
self._client = httpx.AsyncClient(
base_url=base_url.rstrip("/"),
headers={"X-API-Key": api_key.get_secret_value()},
timeout=timeout,
limits=limits,
transport=transport,
trust_env=False,
)
async def __aenter__(self) -> "WeKnoraClient":
return self
async def __aexit__(
self,
exc_type: type[BaseException] | None,
exc_value: BaseException | None,
traceback: TracebackType | None,
) -> None:
await self.aclose()
async def aclose(self) -> None:
await self._client.aclose()
async def search(
self,
*,
query: str,
knowledge_base_id: UUID,
) -> list[dict[str, object]]:
request_id = current_request_id()
headers = {"X-Request-ID": request_id} if request_id is not None else None
try:
response = await self._client.post(
"/api/v1/knowledge-search",
headers=headers,
json={
"query": query,
"knowledge_base_ids": [str(knowledge_base_id)],
},
)
except (httpx.TimeoutException, httpx.NetworkError) as exc:
raise WeKnoraUnavailableError("WeKnora unavailable") from exc
if not response.is_success:
raise WeKnoraBadResponseError("invalid WeKnora response")
try:
payload = response.json()
except ValueError as exc:
raise WeKnoraBadResponseError("invalid WeKnora response") from exc
if not isinstance(payload, dict) or payload.get("success") is not True:
raise WeKnoraBadResponseError("invalid WeKnora response")
data = payload.get("data")
if not isinstance(data, list) or any(not isinstance(item, dict) for item in data):
raise WeKnoraBadResponseError("invalid WeKnora response")
return data