gongzhiyongandOmX
cd2431ece2
Promote the S07 external FastAPI chain from score-only acceptance to a minimal quality-gated flow with refusal detection, retry/fallback recovery, handoff quality checks, and a multi-round consensus gate before final convergence. Constraint: The user asked to fix the documented shortcomings around score-only convergence, weak refusal scoring, and unqualified handoff evidence while continuing the minimal version. Rejected: Replacing the whole coordinator with a production consensus runtime | the minimal fix keeps the existing task pool/convergence shape and adds scenario-level quality gates plus consensus evidence. Confidence: high Scope-risk: moderate Directive: Future S07 runs must keep all_outputs_pass_quality_gate and multi_round_quality_consensus_accepts_chain as required checks before claiming PASS. Tested: .venv/bin/python -B -m unittest tests.test_standard_scenarios; .venv/bin/python -u -B examples/run_continuous_reasoning_acceptance.py; .venv/bin/python -B examples/export_model_agnet_io_report.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; .venv/bin/python -B -m unittest tests.test_model_io_report_audit; git diff --check; docs secret pattern scan. Not-tested: The combined run_standard_scenario_acceptance wrapper was not rerun after report export to avoid creating a newer live run that would make the exported latest-run report stale. Co-authored-by: OmX <omx@oh-my-codex.dev>
64 lines
2.3 KiB
Python
64 lines
2.3 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 [
|
|
"## 场景说明：FastAPI 是什么项目",
|
|
"## 本轮实际做了什么代码 / 测试工作",
|
|
"## 不同 Agnet 的工作怎么实现",
|
|
"## 收敛过程如何发生",
|
|
"## 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（审计摘要）",
|
|
"#### 接手 / 交接机制",
|
|
"原始来源：PostgreSQL `swarm_tasks.output`",
|
|
"质量补救",
|
|
"共识质量门",
|
|
"quality_attempt=1",
|
|
"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",
|
|
"I appreciate the detailed context",
|
|
"What I can actually do",
|
|
"What I cannot do",
|
|
"输出质量风险",
|
|
]:
|
|
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()
|