fix: Windows兼容性修复 + P1-24弱模型优化 + 3.2.9b禁止降级方案 + AirRvr三层审查放行标准

- lock.py: 跨平台进程锁（Unix fcntl / Windows msvcrt / O_CREAT|O_EXCL降级） - eng_mode.py/eng_orchestrator.py: hasattr(os, "getloadavg") Windows防护 - arc_mode.py: 路径分隔符 replace("\\", "/") Windows兼容 - deploy_runtime.py: 修复语法错误（清理 import tempfile 残留） - P1-24(3.2.18): AMBIGUOUS_VERBS歧义词检测 + SAFE_VERBS安全动词 + validate_task_description() - TaskNode.keep_constraints 保留约束字段 + JSON序列化 - _build_graph_from_todo 返回歧义警告 + Arc自检集成 - 3.2.9b: FORBIDDEN_DEGRADATION_PATTERNS + check_forbidden_degradation() - AirRvr三层审查放行标准: ReviewVerdict + evaluate_review_pass() + is_forbidden_pass_reason() - commands/arc.md: 弱模型安全重写（操作类型拆分+保留约束+自检） - commands/do.md/eng.md/rvr.md: 禁止降级方案 + 三层审查标准 - 测试: 7个新测试 + 74全量通过 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-15 09:58:29 +08:00
parent 6130478c96
commit a60d1a0c04
13 changed files with 486 additions and 42 deletions
--- a/test_arc.py
+++ b/test_arc.py
@@ -54,7 +54,7 @@ def test_arc_build_graph():
 | [T-003] 任务3 | DONE | src/c/ | 完成 |
 """)

-        graph, violations = _build_graph_from_todo(todo_path)
+        graph, violations, ambiguity_warnings = _build_graph_from_todo(todo_path)

        # 检查节点数量
        assert len(graph.nodes) >= 3, f"应有至少3个节点，实际: {len(graph.nodes)}"
@@ -66,7 +66,7 @@ def test_arc_build_graph():
        # 检查 Done When 违规检测
        assert len(violations) > 0, "应该有 Done When 不含'测试通过'的违规"

-        print(f"✓ DAG 构建测试通过，节点数: {len(graph.nodes)}, 测试任务: {len(test_nodes)}, 违规: {len(violations)}")
+        print(f"✓ DAG 构建测试通过，节点数: {len(graph.nodes)}, 测试任务: {len(test_nodes)}, 违规: {len(violations)}, 歧义警告: {len(ambiguity_warnings)}")
    return True


@@ -107,6 +107,153 @@ def test_arc_parallel_review():
    return True


+def test_validate_task_description():
+    """P1-24: 测试任务描述歧义词检测"""
+    from air_runtime.review import validate_task_description
+
+    # 包含歧义词
+    warnings = validate_task_description("T-001", "清理旧产品实现并重建新CMake骨架")
+    assert len(warnings) > 0, "应该检测到歧义词'清理'"
+    assert "清理" in warnings[0], f"警告应包含'清理': {warnings[0]}"
+
+    # 不包含歧义词
+    clean_warnings = validate_task_description("T-002", "重构CMakeLists.txt去掉sipclient依赖")
+    assert len(clean_warnings) == 0, f"不应该有歧义词警告: {clean_warnings}"
+
+    # 多个歧义词
+    multi_warnings = validate_task_description("T-003", "清理旧代码并优化模块结构，更新API接口")
+    assert len(multi_warnings) >= 3, f"应该检测到至少3个歧义词: {len(multi_warnings)}"
+
+    print(f"✓ validate_task_description 测试通过，歧义词检测: {len(warnings)}/{len(clean_warnings)}/{len(multi_warnings)}")
+    return True
+
+
+def test_ambiguity_warnings_in_graph():
+    """P1-24: 测试 _build_graph_from_todo 产出歧义警告"""
+    from air_runtime.modes.arc_mode import _build_graph_from_todo
+
+    with tempfile.TemporaryDirectory() as tmpdir:
+        todo_path = Path(tmpdir) / "todo.md"
+        todo_path.write_text("""
+| Task | Status | Files/Dirs | Done When |
+|------|--------|------------|-----------|
+| [T-001] 清理旧模块 | TODO | src/module.cpp | 编译通过 |
+| [T-002] 优化数据库查询性能 | TODO | db/query.cpp | 测试通过 |
+| [T-003] 新增日志模块 | TODO | log/spdlog.cpp | 测试通过 |
+""")
+        graph, violations, ambiguity_warnings = _build_graph_from_todo(todo_path)
+
+        # T-001 "清理" 和 T-002 "优化" 应该触发歧义警告
+        assert len(ambiguity_warnings) >= 2, f"应有至少2个歧义警告，实际: {len(ambiguity_warnings)}"
+        # T-003 "新增" 应该没有歧义
+        ambiguous_task_ids = set()
+        for w in ambiguity_warnings:
+            tid = w.split("]")[0].replace("[", "") if "]" in w else ""
+            ambiguous_task_ids.add(tid)
+        assert "T-003" not in ambiguous_task_ids, f"'新增'不应触发歧义警告: {ambiguity_warnings}"
+
+        print(f"✓ 歧义警告产出测试通过，警告: {len(ambiguity_warnings)}，违规: {len(violations)}")
+    return True
+
+
+def test_forbidden_degradation():
+    """3.2.9b: 测试降级语言检测"""
+    from air_runtime.review import check_forbidden_degradation
+
+    # 包含降级语言
+    found = check_forbidden_degradation("我们先用兜底方案实现，以后再优化")
+    assert len(found) > 0, "应该检测到降级语言"
+    assert "兜底方案" in found or "以后再优化" in found, f"应检测到具体模式: {found}"
+
+    # 不包含降级语言
+    clean = check_forbidden_degradation("按照AirArc设计方案实现，使用RAII管理资源")
+    assert len(clean) == 0, f"不应有降级语言: {clean}"
+
+    # 多种降级语言
+    multi = check_forbidden_degradation("先用临时方案实现，以后再删掉这个兜底方案")
+    assert len(multi) >= 3, f"应检测到多个降级模式: {len(multi)}"
+
+    print(f"✓ 降级语言检测测试通过: {len(found)}/{len(clean)}/{len(multi)}")
+    return True
+
+
+def test_evaluate_review_pass():
+    """AirRvr: 测试三层审查放行标准"""
+    from air_runtime.review import evaluate_review_pass, is_forbidden_pass_reason
+
+    # 全部通过
+    result = evaluate_review_pass(
+        code_to_design_table=[
+            {"designPoint": "使用RAII管理资源", "status": "aligned"},
+            {"designPoint": "接口使用智能指针", "status": "aligned"},
+        ],
+        sdb_report={"findings": []},
+        test_results={"suites": [{"name": "unit", "status": "pass"}]},
+    )
+    assert result.verdict == "pass", f"全部通过应为 pass，实际: {result.verdict}"
+    assert result.layer1_pass and result.layer2_pass and result.layer3_pass
+
+    # 第一层有 divergent → fail
+    result2 = evaluate_review_pass(
+        code_to_design_table=[
+            {"designPoint": "使用RAII管理资源", "status": "divergent"},
+        ],
+        sdb_report={"findings": []},
+        test_results={"suites": [{"name": "unit", "status": "pass"}]},
+    )
+    assert result2.verdict == "fail", f"第一层有divergent应为fail，实际: {result2.verdict}"
+    assert not result2.layer1_pass
+
+    # 第一层通过，第二层有 critical finding → conditional-pass
+    result3 = evaluate_review_pass(
+        code_to_design_table=[
+            {"designPoint": "使用RAII管理资源", "status": "aligned"},
+        ],
+        sdb_report={"findings": [{"severity": "critical", "description": "use-after-free"}]},
+        test_results={"suites": [{"name": "unit", "status": "pass"}]},
+    )
+    assert result3.verdict == "conditional-pass", f"应为conditional-pass，实际: {result3.verdict}"
+
+    # 第一层有 missing → fail
+    result4 = evaluate_review_pass(
+        code_to_design_table=[
+            {"designPoint": "使用RAII管理资源", "status": "aligned"},
+            {"designPoint": "AES加密", "status": "missing"},
+        ],
+        sdb_report={"findings": []},
+        test_results={"suites": []},
+    )
+    assert result4.verdict == "fail", f"第一层有missing应为fail，实际: {result4.verdict}"
+
+    # 禁止的表面原因
+    assert is_forbidden_pass_reason("测试全绿") == True
+    assert is_forbidden_pass_reason("编译通过无报错") == True
+    assert is_forbidden_pass_reason("代码实现正确，三层审查均通过") == False
+
+    print(f"✓ 三层审查放行标准测试通过: pass/fail/cond-pass/forbidden")
+    return True
+
+
+def test_keep_constraints_in_tasknode():
+    """P1-24: 测试 TaskNode.keep_constraints 字段"""
+    from air_runtime.task_graph import TaskNode
+
+    node = TaskNode(
+        id="T-001",
+        task="重构 CMakeLists.txt 去掉 sipclient 依赖",
+        keep_constraints=["src/ 目录下所有现有源文件不得删除或修改"],
+    )
+    assert node.keep_constraints == ["src/ 目录下所有现有源文件不得删除或修改"]
+    assert len(node.keep_constraints) == 1
+
+    # 空约束
+    node2 = TaskNode(id="T-002", task="新增日志模块")
+    assert node2.keep_constraints == []
+
+    print("✓ TaskNode.keep_constraints 字段测试通过")
+    return True
+
+
 def main():
    print("=" * 50)
    print("Arc Mode 功能测试")
@@ -116,6 +263,11 @@ def main():
        ("三阶段门控", test_arc_phase_gate),
        ("DAG 构建", test_arc_build_graph),
        ("并行审查", test_arc_parallel_review),
+        ("P1-24 歧义词检测", test_validate_task_description),
+        ("P1-24 歧义警告产出", test_ambiguity_warnings_in_graph),
+        ("3.2.9b 降级语言检测", test_forbidden_degradation),
+        ("三层审查放行标准", test_evaluate_review_pass),
+        ("P1-24 keep_constraints", test_keep_constraints_in_tasknode),
    ]

    passed = 0