Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
Python ai4sciencedocument-analysisdocxextract-datalayout-analysisocrparserpdfpdf-converterpdf-extractor-llmpdf-extractor-pretrainpdf-extractor-ragpdf-parserpptxpythonxlsx
test: allow bounded runtime for cascaded filename regression
myhloli104eacbfbb64
diff --git a/.github/workflows/cli.yml b/.github/workflows/cli.ymlindex 83ad6318..3e3c145f 100644--- a/.github/workflows/cli.yml+++ b/.github/workflows/cli.yml@@ -131,7 +131,7 @@ jobs:if: runner.os != 'Linux'run: |uv run --no-project --no-sync python -m pytest -o addopts='' --strict-markers \- --junitxml=build/ci/filenames.xml \+ --durations=10 --junitxml=build/ci/filenames.xml \-k 'path_extension or parse_filename or csv or task_filename' \tests/unittest/test_filetypes.py \tests/unittest/test_kit_commands.py \diff --git a/tests/unittest/test_task_tiers.py b/tests/unittest/test_task_tiers.pyindex a4f30617..3cd62ebe 100644--- a/tests/unittest/test_task_tiers.py+++ b/tests/unittest/test_task_tiers.py@@ -95,19 +95,30 @@ def _request_body(inputs: list[tuple[str, bytes]], options: dict[str, Any]) -> dreturn {"files": [{"file_name": name, "bytes": len(data)} for name, data in inputs], **options}-async def _complete(client: httpx.AsyncClient, task: dict[str, Any], inputs: list[tuple[str, bytes]]) -> dict[str, Any]:+async def _complete(+ client: httpx.AsyncClient,+ task: dict[str, Any],+ inputs: list[tuple[str, bytes]],+ *,+ timeout_seconds: float = 20,+) -> dict[str, Any]:"""上传真实源文件并等待终态,执行和结果获取均经过公共接口。"""for item, (_name, data) in zip(task["files"], inputs):response = await client.put(item["upload"]["url"], content=data, headers=item["upload"]["headers"])assert response.status_code == 200, response.text- async with asyncio.timeout(20):- while True:- response = await client.get(f"/v1/tasks/{task['task_id']}")- assert response.status_code == 200, response.text- result = response.json()- if result["status"] in TERMINAL_TASK_STATUSES:- return result- await asyncio.sleep(0.01)+ result: dict[str, Any] | None = None+ try:+ async with asyncio.timeout(timeout_seconds):+ while True:+ response = await client.get(f"/v1/tasks/{task['task_id']}")+ assert response.status_code == 200, response.text+ result = response.json()+ if result["status"] in TERMINAL_TASK_STATUSES:+ return result+ # 多层 ASGI 请求共享事件循环,避免高频查询挤占上传和解析任务。+ await asyncio.sleep(0.05)+ except TimeoutError:+ pytest.fail(f"Task did not finish within {timeout_seconds}s; last response: {result!r}")async def _archive(client: httpx.AsyncClient, item: dict[str, Any]) -> dict[str, bytes]:@@ -369,7 +380,8 @@ def test_native_csv_filename_and_storage_boundary(tmp_path: Path, deployment: stassert response.status_code == 202, response.texttask = response.json()assert app.state.task_store._records[task["task_id"]].options.tier == "flash"- result = await _complete(client, task, inputs)+ # 四个文件经过两层 Router、磁盘存储和真实导出;这里验证正确性,不设 20 秒性能门槛。+ result = await _complete(client, task, inputs, timeout_seconds=60)assert result["status"] == "completed", resultassert [item["file_name"] for item in result["files"]] == [name for name, _data in inputs]for item in result["files"]: