Files
knowledge-adapter-service/tests/test_content_budget.py
T
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

35 lines
1.1 KiB
Python

from knowledge_adapter.content_budget import TRUNCATION_MARKER, truncate_content
def test_plain_content_is_truncated_with_explicit_marker() -> None:
limit = len(TRUNCATION_MARKER) + 5
result = truncate_content("abcdefghij" * 10, max_chars=limit)
assert result == f"abcde{TRUNCATION_MARKER}"
assert len(result) == limit
def test_truncation_never_splits_markdown_image_node() -> None:
content = (
"prefix "
"![image](https://assets.example.com/i/550e8400-e29b-41d4-a716-446655440000)"
" trailing text"
)
limit = len(TRUNCATION_MARKER) + len("prefix ![image](https://assets.")
result = truncate_content(content, max_chars=limit)
assert result == f"prefix {TRUNCATION_MARKER}"
assert len(result) <= limit
def test_truncation_never_splits_fenced_code_block() -> None:
content = "intro\n```python\nprint('sensitive')\n```\n" + ("after" * 20)
limit = len(TRUNCATION_MARKER) + len("intro\n```python\nprint")
result = truncate_content(content, max_chars=limit)
assert result == f"intro\n{TRUNCATION_MARKER}"
assert result.count("```") == 0