Add report audit scenario

Extend the Agent standard matrix with a report-audit scenario so model input, output, handoff, and secret-safety evidence are tested instead of remaining narrative-only.

Constraint: The user requested another test pass and expanded Agent/swarm testing scenarios under docs/.

Rejected: Treating the model I/O report as untested documentation | it would leave the handoff and input/output evidence unguarded.

Confidence: high

Scope-risk: moderate

Directive: Keep model I/O reports under docs/ and redact secret-shaped values during export.

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: Large-scale concurrent 3/5/7 worker load and external browser rendering were not run.

Co-authored-by: OmX <omx@oh-my-codex.dev>

examples/export_model_agnet_io_report.py

@@ -14,6 +14,8 @@ from swarm_minimal.local_env import load_project_env
 
 
 RUN_IDS = [
+    "04c641d170fe4ea7aa3d882d9df37cca",
+    "c592a7ca4c0f4e02b93a1390b62d0af7",
     "063632eeb17b45c197aa866066158667",
     "3e8e58ae4e084bc8b90cf5c46f8992f3",
     "78f189ccd1924ed0a4fb0a0a447ad449",
@@ -46,6 +48,12 @@ TEST_SCENARIOS = (
         "purpose": "用真实 Azure PostgreSQL、Redis、Blob 和 NewAPI 跑 7 步连续推理链。",
         "evidence": "本报告下方每个 live run 的 task.input / task.output / handoff 记录。",
     },
+    {
+        "id": "S08",
+        "name": "model_io_report_audit",
+        "purpose": "验证本报告包含场景、输入、输出、交接证据，且没有明显真实密钥样式。",
+        "evidence": "`unittest tests.test_model_io_report_audit`",
+    },
 )
 
 OUTPUT_PATH = ROOT / "docs" / "MODEL_AGNET_IO_REPORT.zh-CN.md"
@@ -85,7 +93,7 @@ def build_report(store: PostgresRedisBlobSwarmStore) -> str:
     sections.extend(
         [
             "",
-            "最新重跑结论：S01-S07 全部 PASS；最新 S07 live run 会排在下方第一个。",
+            "最新重跑结论：S01-S08 全部 PASS；最新 S07 live run 会排在下方第一个。",
             "",
         ]
     )
@@ -123,7 +131,7 @@ def render_run(convergence: dict[str, object], tasks: dict[str, dict[str, object
     for index, observation in enumerate(convergence["observations"], start=1):
         task_id = observation["task_id"]
         task = tasks[task_id]
-        output = str(task.get("output") or "")
+        output = redact_sensitive_text(str(task.get("output") or ""))
         model = infer_model(task, output)
         lines.extend(
             [
@@ -148,7 +156,7 @@ def render_run(convergence: dict[str, object], tasks: dict[str, dict[str, object
                 "#### 本次任务输入 task.input",
                 "",
                 "```text",
-                str(task["input"]).strip(),
+                redact_sensitive_text(str(task["input"])).strip(),
                 "```",
                 "",
                 "#### Agnet / 模型实际输出 task.output",
@@ -162,6 +170,19 @@ def render_run(convergence: dict[str, object], tasks: dict[str, dict[str, object
     return lines
 
 
+def redact_sensitive_text(text: str) -> str:
+    replacements = [
+        (r"sk-[A-Za-z0-9]{20,}", "sk-<redacted>"),
+        (r"AccountKey=[^;\s`]+", "AccountKey=<redacted>"),
+        (r"password=[^,;\s`]+", "password=<redacted>"),
+        (r"BEGIN [A-Z ]*PRIVATE KEY", "BEGIN <redacted> PRIVATE KEY"),
+    ]
+    redacted = text
+    for pattern, replacement in replacements:
+        redacted = re.sub(pattern, replacement, redacted, flags=re.IGNORECASE)
+    return redacted
+
+
 def handoff_description(goal: str, run_id: str, task: dict[str, object], output: str) -> str:
     if goal.startswith("连续性长推理场景"):
         match = re.search(r"chain_edge=([^;\\n]+)", output)

examples/run_academic_standard_evaluation.py

@@ -91,7 +91,7 @@ def main() -> None:
         },
         "pass_condition": {
             "local_academic_gate": "all A01-A05 checks pass",
-            "full_standard_gate": "local_academic_gate plus S07 live Azure/NewAPI scenario",
+            "full_standard_gate": "local_academic_gate plus S07 live Azure/NewAPI scenario and S08 model I/O report audit",
         },
     }
     print(json.dumps(report, ensure_ascii=False, indent=2))

examples/run_continuous_reasoning_acceptance.py

@@ -523,6 +523,8 @@ def no_required_nats_or_cosmos(text: str) -> bool:
         "不引入",
         "不使用",
         "不依赖",
+        "不可",
+        "不可作为",
         "无需",
         "不要",
         "不做",
@@ -532,6 +534,10 @@ def no_required_nats_or_cosmos(text: str) -> bool:
         "未涉及",
         "已排除",
         "排除",
+        "反例",
+        "违反",
+        "拒绝",
+        "严重错误",
         "误依赖",
         "非必需",
         "no ",

examples/run_standard_scenario_acceptance.py

@@ -45,6 +45,15 @@ SCENARIOS = [
         "command": [sys.executable, "-u", "-B", "examples/run_continuous_reasoning_acceptance.py"],
         "parse_json": True,
     },
+    {
+        "id": "S08",
+        "name": "model_io_report_audit",
+        "layer": "report-audit",
+        "given": "generated docs/MODEL_AGNET_IO_REPORT.zh-CN.md",
+        "when": "audit scenario coverage, task input/output sections, handoff evidence, and obvious secret patterns",
+        "then": "the report is human-auditable and does not contain obvious secret values",
+        "command": [sys.executable, "-B", "-m", "unittest", "tests.test_model_io_report_audit"],
+    },
 ]