gongzhiyongandOmX
dc2b166e60
Replace the self-referential S07 code task with a pinned fastapi/fastapi GitHub scenario so the live Agent standard tests evaluate an external complex codebase instead of the local harness project. Constraint: The user explicitly rejected using this project as the code target for the live scenario. Rejected: Keeping swarm-minimal as the S07 code target | it would keep validating the harness against itself. Confidence: high Scope-risk: moderate Directive: Keep S07 target files external to this repository unless the user explicitly asks for a local-harness scenario. Tested: .venv/bin/python -u -B examples/run_standard_scenario_acceptance.py; .venv/bin/python -B -m unittest discover -s tests; .venv/bin/python -B -m py_compile swarm_minimal/*.py examples/*.py tests/*.py; .venv/bin/python -u -B examples/run_academic_standard_evaluation.py; git diff --check; docs secret-pattern scan. Not-tested: Applying the proposed FastAPI patch inside the external fastapi/fastapi repository was not run; S07 is a live Agent reasoning and evidence-chain test. Co-authored-by: OmX <omx@oh-my-codex.dev>
52 lines
1.7 KiB
Python
52 lines
1.7 KiB
Python
from pathlib import Path
|
|
import re
|
|
import unittest
|
|
|
|
|
|
ROOT = Path(__file__).resolve().parents[1]
|
|
REPORT = ROOT / "docs" / "MODEL_AGNET_IO_REPORT.zh-CN.md"
|
|
|
|
|
|
class ModelIoReportAuditTests(unittest.TestCase):
|
|
def test_report_exposes_scenarios_inputs_outputs_and_handoff(self) -> None:
|
|
text = REPORT.read_text(encoding="utf-8")
|
|
|
|
for required in [
|
|
"## 本轮测试场景补充",
|
|
"| S01 | syntax_import_sanity |",
|
|
"| S02 | unit_regression |",
|
|
"| S03-S06 | deterministic_standard_scenarios |",
|
|
"| S07 | live_external_github_code_reasoning |",
|
|
"| S08 | model_io_report_audit |",
|
|
"fastapi/fastapi",
|
|
"ecace740f3eaccb1aba152cf1de79477095c56f4",
|
|
"fastapi/routing.py",
|
|
"#### 本次任务输入 task.input",
|
|
"#### Agnet / 模型实际输出 task.output",
|
|
"#### 接手 / 交接机制",
|
|
"chain_edge=",
|
|
]:
|
|
self.assertIn(required, text)
|
|
for forbidden in [
|
|
"为 swarm-minimal 设计可恢复的大规模代码任务推理链",
|
|
"swarm_minimal/core.py",
|
|
"swarm_minimal/newapi_agnet.py",
|
|
"swarm_minimal/azure_store.py",
|
|
]:
|
|
self.assertNotIn(forbidden, text)
|
|
|
|
def test_report_does_not_contain_obvious_secret_values(self) -> None:
|
|
text = REPORT.read_text(encoding="utf-8")
|
|
forbidden_patterns = [
|
|
r"sk-[A-Za-z0-9]{20,}",
|
|
r"AccountKey=[^<\s`]+",
|
|
r"password=[^<\s`]+",
|
|
r"BEGIN [A-Z ]*PRIVATE KEY",
|
|
]
|
|
for pattern in forbidden_patterns:
|
|
self.assertIsNone(re.search(pattern, text, flags=re.IGNORECASE))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|