feat: P1-19 P1-20 实现 - 边界测试强制 + 高风险审计 + UI Skill 路由

P1-19.1: Arc 边界测试强制 - TaskNode 新增 test_required 字段 - _inject_boundary_tests() 为每个模块注入接口测试和单元测试任务 - Done When 验证必须包含"测试通过" P1-19.2: AirRvr 高风险审计 - 新增 HighRiskAudit, HighRiskFinding 数据类 - ReviewReport 新增 highRiskAudit 字段，含 lifecycle/nullPointer/danglingPointer/exceptionSafety/concurrency + overallRisk + deliveryVerdict - 序列化/反序列化支持 P1-19.3: block-release 集成 - dispatch_worker_group() 派发前扫描最新审查报告 - deliveryVerdict=block-release 时阻止所有后续派发 - 记录 eng.blocked 事件 P1-20: frontend-design Skill 集成 - is_ui_task() UI 任务检测 - ensure_frontend_design_skill() 自动安装 Skill - route_ui_task() UI 任务路由决策 - enter_worker() 集成 UI 检测，skill 不可用时阻止执行 - commands/do.md 更新 UI 处理说明 - SKILL.md 新增 INV-12/INV-13/INV-14 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-06-10 17:06:48 +08:00
commit e73a4da354
54 changed files with 6054 additions and 0 deletions
--- a/lib/air_runtime/evidence_gate.py
+++ b/lib/air_runtime/evidence_gate.py
@@ -0,0 +1,74 @@
+"""
+任务类型感知的证据门控 — V2 P0-1 修复。
+替代 V1 无差别触发 AirXDB 的逻辑，根据任务特征差异化要求证据类型。
+"""
+
+from __future__ import annotations
+
+import enum
+from dataclasses import dataclass
+
+
+class EvidenceClass(enum.Enum):
+    GUI_REQUIRED = "gui_required"          # 需要截图/GUI 操作验证
+    NETWORK_REQUIRED = "network_required"   # 需要抓包/流量验证
+    STATIC_ANALYSIS = "static_analysis"    # 需要静态分析
+    CODE_ONLY = "code_only"                # 代码级验证即可
+
+
+@dataclass
+class EvidenceGatePolicy:
+    """基于任务特征的差异化证据要求。
+
+    关键词匹配 → 确定性分类，零额外 API 调用，可测试可覆盖。
+    用户可在 todo.md 中用 [no-xdb] / [no-ndb] 标记显式跳过。
+    """
+
+    GUI_INDICATORS: tuple[str, ...] = (
+        "gui", "ui", "render", "layout", "dialog", "osd",
+        "overlay", "visual", "screenshot", "display",
+        "widget", "pane", "toolbar", "settings_dialog",
+        "canvas", "button", "window", "popup", "menu",
+        "drm", "kms", "opengl", "vulkan",
+    )
+
+    NETWORK_INDICATORS: tuple[str, ...] = (
+        "network", "rtsp", "http", "tcp", "udp", "tls",
+        "dns", "proxy", "socket", "stream", "port",
+        "packet", "pcap", "bandwidth", "latency",
+    )
+
+    STATIC_ANALYSIS_INDICATORS: tuple[str, ...] = (
+        "cppcheck", "clang-tidy", "mypy", "ruff", "lint",
+        "static analysis", "compile_commands",
+    )
+
+    SKIP_MARKERS: tuple[str, ...] = ("[no-xdb]", "[no-ndb]", "[no-sdb]")
+
+    def classify(self, task_text: str, task_id: str = "", skip_overrides: list[str] | None = None) -> EvidenceClass:
+        text = task_text.lower()
+        skips = set(skip_overrides or [])
+        for marker in self.SKIP_MARKERS:
+            if marker in text:
+                skips.add(marker)
+
+        has_gui = any(kw in text for kw in self.GUI_INDICATORS)
+        has_net = any(kw in text for kw in self.NETWORK_INDICATORS)
+        has_static = any(kw in text for kw in self.STATIC_ANALYSIS_INDICATORS)
+
+        if has_gui and "[no-xdb]" not in skips:
+            return EvidenceClass.GUI_REQUIRED
+        if has_net and "[no-ndb]" not in skips:
+            return EvidenceClass.NETWORK_REQUIRED
+        if has_static and "[no-sdb]" not in skips:
+            return EvidenceClass.STATIC_ANALYSIS
+        return EvidenceClass.CODE_ONLY
+
+    def required_evidence_for(self, evidence_class: EvidenceClass) -> list[str]:
+        evidence_map = {
+            EvidenceClass.GUI_REQUIRED: ["screenshot", "gui-operation-validation"],
+            EvidenceClass.NETWORK_REQUIRED: ["packet-capture", "connectivity-verification"],
+            EvidenceClass.STATIC_ANALYSIS: ["static-analysis-report"],
+            EvidenceClass.CODE_ONLY: ["code-review", "test-results"],
+        }
+        return evidence_map.get(evidence_class, ["code-review"])