先看结论
基于现有公开资料生成，最后决策仍应核对原始来源。
An advisory loop-breaker, not a model-facing tool: it never appears in the tool list, never vetoes or rewrites a call, and adds exactly one behavior — it watches each agent's stream of tool calls, counts runs of consecutive calls to the same tool with identical canonicalized arguments, and at configured run lengths injects an escalating advisory reminder telling the model to stop repeating itself, re-read the last result, and either change approach or conclude. The decision (retry differently, gather more evidence, or finish) stays entirely with the model: a legitimately repeated call is delayed by nothing and blocked by nothing. Decision record: [the repeat-tool-reminder Agent Note](../../../.agents/notes/archived/feature/2026-07-08-repeat-tool-guard.md).
能力
它能让 Agent / 使用者做什么。
- 适用 Agent：DeepSeek Harness
- 适配模型：DeepSeek
安装与获取
可复现安装方式。
@deepseek-ai/dsh-repeat-tool-reminder
来源与核实
保留来源、时间与置信度，供回溯。
实效证据
来源可信不等于任务有效。
暂无通过审核、可复现的同任务 A/B 运行证据；本档案仅证明来源可信，不代表实测有效。