feat(compute): Claude 系列 defaultEffort 统一为 xhigh，presetDataVersion → 87 (#73)

Anthropic 对 Fable 5 / Opus 5 / Sonnet 5 的建议是编程与智能体场景用 xhigh
（Claude Code 自身默认即 xhigh），而此前沿用的是 API 默认值 high。DesireCore
是智能体操作系统，主力场景就是编程与长程智能体任务，故对齐到 xhigh。

两个 Anthropic provider 的 fable-5 / opus-5 / sonnet-5 同步调整，
extra.reasoning.defaultEffort 与顶层文档性 extra.defaultEffort 保持一致。
Haiku 4.5 不支持 effort 参数，无 reasoning 声明，不受影响。

注意：这会抬高默认 token 消耗；用户仍可在模型选择器按会话下调档位。
OpenAI Codex 的 per-model defaultEffort（low/medium/medium）是按模型分别调过的，
不属于本次对齐范围。

compute/providers/anthropic.json

@@ -56,7 +56,7 @@
             "xhigh",
             "max"
           ],
-          "defaultEffort": "high"
+          "defaultEffort": "xhigh"
         },
         "samplingParametersDeprecated": true,
         "pricingNotes": "Prices are per 1M tokens. Full 1M context is billed at standard pricing."
@@ -106,9 +106,9 @@
             "xhigh",
             "max"
           ],
-          "defaultEffort": "high"
+          "defaultEffort": "xhigh"
         },
-        "defaultEffort": "high",
+        "defaultEffort": "xhigh",
         "samplingParametersDeprecated": true,
         "pricingNotes": "Prices are per 1M tokens. Full 1M context is billed at standard pricing."
       }
@@ -161,9 +161,9 @@
             "xhigh",
             "max"
           ],
-          "defaultEffort": "high"
+          "defaultEffort": "xhigh"
         },
-        "defaultEffort": "high",
+        "defaultEffort": "xhigh",
         "samplingParametersDeprecated": true
       }
     },