dsh-loop-continue
续跑「叙述了下一步动作却没调用工具」就结束的 agent 轮次:插件在 agent/turn-stopping 回放该轮日志,让裁判模型回答一次 true/false,命中的话把同一轮再推进一步。
Resumes an agent turn that ended after narrating its next action without calling a tool: the guard replays the turn log on agent/turn-stopping, asks a judge model one true/false question, and steers the same turn to run one more step.
怎么安装
dsh plugin add dsh-loop-continue 简介
dsh-loop-continue Continue a DeepSeek Harness agent turn when the model only *narrated* its next action and forgot the tool call. The agent loop closes a turn as completed the moment a step emits text and no tool call. A model that writes "now I will re-apply the change" and stops looks finished to the loop, even though the work is half done. This plugin listens on agent/turn-stopping, replays the current turn's own session log, and only asks a judge model one strict true/false question when the shape matches that failure mode. true steers the same turn to run one more step; false (or an unpar…
推荐参考
信息
- 协议
- MIT
- 语言
- JavaScript
- GitHub 星标
- 0
- 月下载
- 367
- 最近更新
- 2026-09-11
- 创建于
- 2026-09-10
基础安全检查
- 检查结果
- 无
- 收录来源
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- 主题标签
- agent-loop, cordis, deepseek-harness, dsh, dsh-plugin
同类推荐
dsh-memory
FuRongJun-1999/dsh-memory
白箱AGI架构探索:元认知(自我认知循环)、持续学习(知识飞轮)、世界模型(条件空间+语义时空图)、自我改进(自举纪律)、零LLM白箱管线与可审计信任护栏。
dsh-engram
kenz1117/dsh-engram
跨会话长期记忆插件,以「记忆宫殿」隐喻重构 agent 长期记忆:双层 SQLite 分库(用户级 + 按 git origin 隔离的项目级)、FTS5 + 本地向量 RRF 融合与新鲜度/命中排序 boost、从会话日志自动摄取(含末轮)、来源审计链、巩固蒸馏与衰减遗忘,以及设置页「记忆库」面板(走廊拓扑、导览管家、翻新清单)。
dsh-answer-reviewer
bycall/dsh-answer-reviewer
智能体回答审查器:每一轮 agent 的最终输出由独立 LLM 重新打分(1-100),低于阈值时携带具体反馈引导 agent 自我修正。配置经 127.0.0.1 本地 HTTP 服务实时修改,也支持 dsh-better-sidebar 侧栏配置页。
dsh-quality-review
CAI-MH/dsh-quality-review
每轮回复结束时用独立审查模型审核输出,判定不合格则引导 agent 修复,每轮最多追问 2 次;可注入 SOP 文件夹标准作为额外审核维度。