feat(flywheel): golden case 管理 API 与评测单测

- 新增 GoldenCaseCreate/Read、GoldenEvalRequest/Read schema
- 新增 3 个端点：创建 golden case、按规则列表、手动触发 golden 评测
  （不入门禁，供运营试跑）
- 单测 15 passed：单条 hit/severity 比对、集合 accuracy/precision/recall
  聚合、空集降级、100% 通过/失败拦截、feature flag、异常降级
- 回归 test_agent_asset_service 27 passed（1 个预存失败与本改动无关）

server/src/app/schemas/agent_asset.py

@@ -204,6 +204,46 @@ class AgentAssetRiskRuleReportRequest(BaseModel):
     note: str | None = Field(default=None, max_length=1000)
 
 
+class GoldenCaseCreate(BaseModel):
+    case_key: str = Field(..., max_length=160)
+    rule_code: str | None = Field(default=None, max_length=120)
+    scene: str = Field(default="", max_length=50)
+    name: str = Field(default="", max_length=120)
+    values: dict[str, Any] = Field(default_factory=dict)
+    expected_hit: bool = True
+    expected_severity: str | None = Field(default=None, max_length=20)
+    note: str | None = None
+
+
+class GoldenCaseRead(BaseModel):
+    id: str
+    case_key: str
+    rule_code: str | None = None
+    scene: str = ""
+    name: str = ""
+    values: dict[str, Any] = Field(default_factory=dict)
+    expected_hit: bool = True
+    expected_severity: str | None = None
+    note: str | None = None
+    status: str = "active"
+    source: str = "manual"
+
+
+class GoldenEvalRequest(BaseModel):
+    version: str | None = Field(default=None, max_length=30)
+
+
+class GoldenEvalRead(BaseModel):
+    total: int = 0
+    passed_count: int = 0
+    failed_count: int = 0
+    accuracy: float = 0.0
+    precision: float = 0.0
+    recall: float = 0.0
+    all_passed: bool = True
+    results: list[dict[str, Any]] = Field(default_factory=list)
+
+
 class AgentAssetRiskRuleSimulationAttachment(BaseModel):
     name: str = Field(default="", max_length=240)
     content_type: str | None = Field(default=None, max_length=120)