政策產生：每個政策驗證

使用政策編寫服務從自然語言產生政策時，驗證和分析會在產生期間根據個別政策進行。

運作方式

範例：產生和驗證政策

擷取產生結果是一個兩步驟的程序：首先檢查產生狀態，然後列出產生的資產以查看政策及其驗證問題清單。

開始產生政策：

aws bedrock-agentcore-control start-policy-generation \
  --policy-engine-id MyEngine-abc123 \
  --name RefundPolicy \
  --content '{
    "rawText": "Allow customer service agents to process refunds up to 500 dollars for orders placed within the last 30 days"
  }' \
  --resource '{
    "arn": "arn:aws:bedrock-agentcore:us-east-1:123456789012:gateway/MyGateway-xyz789"
  }'

回應包含政策產生 ID 和狀態：

{
  "policyGenerationId": "RefundPolicy-def456",
  "policyEngineId": "MyEngine-abc123",
  "status": "GENERATING"
}

使用 get-policy-generation 檢查產生狀態：

aws bedrock-agentcore-control get-policy-generation \
  --policy-engine-id MyEngine-abc123 \
  --policy-generation-id RefundPolicy-def456

回應會顯示整體產生狀態：

{
  "policyGenerationId": "RefundPolicy-def456",
  "status": "GENERATED",
  "statusReasons": []
}

一旦狀態為 GENERATED ，請列出產生的資產以擷取政策及其每個政策的驗證問題清單：

aws bedrock-agentcore-control list-policy-generation-assets \
  --policy-engine-id MyEngine-abc123 \
  --policy-generation-id RefundPolicy-def456

回應包含每個產生的政策及其 Cedar 定義和驗證調查結果：

{
  "policyGenerationAssets": [
    {
      "policyGenerationAssetId": "asset-1",
      "definition": {
        "cedar": {
          "statement": "permit(\n  principal is AgentCore::OAuthUser,\n  action == AgentCore::Action::\"RefundTool___process_refund\",\n  resource == AgentCore::Gateway::\"arn:aws:bedrock-agentcore:us-east-1:123456789012:gateway/MyGateway-xyz789\"\n) when {\n  context.input.amount <= 500\n};"
        }
      },
      "findings": [
        {
          "type": "VALID"
        }
      ],
      "rawTextFragment": "Allow customer service agents to process refunds up to 500 dollars"
    },
    {
      "policyGenerationAssetId": "asset-2",
      "definition": {
        "cedar": {
          "statement": "permit(\n  principal,\n  action == AgentCore::Action::\"RefundTool___view_order_history\",\n  resource\n);"
        }
      },
      "findings": [
        {
          "type": "ALLOW_ALL",
          "description": "Overly Permissive: Policy Engine will allow every request for the specified principal (AgentCore::OAuthUser), action (RefundTool___view_order_history) and resource (gateway/*) combination if the policy is added or updated"
        }
      ],
      "rawTextFragment": "Allow customer service agents to view order history"
    }
  ]
}

每個政策的驗證問題清單

每個產生的政策資產都包含 物件findings陣列，每個Finding都有 type和 description 。下列範例顯示不同的問題清單類型：

通過驗證和分析的政策：

{
  "findings": [
    {
      "type": "VALID"
    }
  ]
}

標記為過度寬鬆的政策：

{
  "findings": [
    {
      "type": "ALLOW_ALL",
      "description": "Overly Permissive: Policy Engine will allow every request for the specified principal (AgentCore::OAuthUser), action (RefundTool___view_order_history) and resource (gateway/*) combination if the policy is added or updated"
    }
  ]
}

無法從自然語言輸入產生的政策：

{
  "findings": [
    {
      "type": "NOT_TRANSLATABLE",
      "description": "Unsupported Condition Error: The request includes conditions that rely on data or attributes currently not supported."
    }
  ]
}

產生政策的常見調查結果

下表說明可針對產生的政策傳回的調查結果類型：