Outcome Monitors: Recovery Affordances for Silent Tool Failures

工具调用的静默失败（cached error page、格式正确的错误数据）会以正确格式到达 agent 并被当作事实消费

从任务无关轨迹或公开 schema 中挖掘结果契约（outcome contracts），违约时保留结果并发出恢复建议（affordance，非强制覆盖）

在多个工具调用场景中检测到主流 agent 无法发现的静默失败；非绑定建议比强制覆盖更鲁棒

实时 agent 工具调用链中静默失败会导致错误传播，Outcome Monitor 是轻量防线

When a tool call times out, the agent sees the failure and can route around it. A cached error page or negative price can instead arrive in the expected format and be consumed as fact. We introduce Outcome Monitors, which detect violations of outcome contracts mined from task-disjoint traces or derived from public schemas. On a violation, the monitor preserves the result and issues a nonbinding receipt naming the violated property and public recovery tools. In frozen, prespecified evaluations wi