DeepSeek Harness Plugin Hub

Publish and manage complete Harness Profiles. Discover Plugins for your next setup.

Explore

PluginsPresetsDocsNews

Community

Publish a pluginContactReport an issue

Resources

Plugin Hub on GitHubDeepSeek HarnessSystem statusPrivacy notice
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

Independent and unofficial. Not affiliated with, authorized by, or endorsed by DeepSeek.

Task Effort — DSH Plugin for DeepSeek Harness
DeepSeek Harness Plugin Hub
ProfilesPluginsCategoriesNewsDocsSign inManage Profiles
ProfilesPluginsCategoriesNewsDocsSign in
← Plugins
T

dsh-task-effort

Task Effort

Auto-adjust model reasoning effort per task: off/low/high/max with task classification, peak-pricing-period capping, countdown notices, and in-turn error escalation

The plugin will be installed here. Keep web if you are unsure.

npx -y @deepseek-ai/dsh plugin --profile web add github:zhangzhenwen1/dsh-task-effort#05822c5cef94bf2acca61830a23192dfb932c753
READMECompatibilityVersions

Compatibility and provenance

Task Effort is published as dsh-task-effort and currently resolves to version 0.1.0. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.

DSH compatibility
*
Runtime surfaces
any
Release source
github
Registry updated
8/30/2026

Versions

0.1.0stable
8/30/2026

Related plugins

Loading related plugins…

Latest
0.1.0
DSH
*
HMR
Process restart
Tree shaking
Safe tree shaking not declared
Unpacked size
Unavailable
Files
Unavailable
Surface
any
License
MIT
Source
github
GitHub
★ 0
Weekly downloads
0
Last push
8/30/2026
View source ↗
README badge

Click the badge to copy Markdown for your README.

Do you maintain this Plugin?Claim benefit · Priority security scan

Verify the GitHub repository declared in package.json to manage this listing. After you claim it, Hub will prioritize a security scan of the current version and publish the result when it passes.

Claim this Plugin →
Report an issue

Related plugins

More verified plugins in models-usage.

Usage@linxin666/dsh-usageUsage statistics plugin for the dsh web GUI: per-provider balance and coding-plan quota detection plus a live token usage ledger, with a dedicated pet bubble for the current providerWhale Widgetdsh-whale-widgetDeepSeek balance whale widget in the bottom-right corner of the DSH Web interface: balance/today’s usage/peak-off-peak pricing, customizable bubble click sequence (text/balance/today/peak-off-peak/image/random phrases and parallel weighted selection), per-line styles and fonts, floating quick editinUsage Stats@ychris12138/dsh-usage-statsToken usage heatmap, provider balances, and subscription quotas for the dsh web GUICodex Connectdsh-codex-connectChatGPT OAuth and Codex models for DeepSeek Harness.

README

dsh-task-effort — 根据任务自动调整模型 effort

DSH 插件:每次 LLM 调用前,根据当前任务自动决定模型的推理强度 reasoningEffort(DeepSeek 支持 off / high / max),不再全局固定一个档位。

工作原理

DSH 的 agent 循环在每次模型调用前会走 agent/request waterfall(dsh-agent-loop 的 buildRequest),插件在瀑布的最外层改写 reasoningEffort,因此最终生效, 优先级高于模型选择器/设置里的默认 effort。

判定时机:agent/pre-step(每步执行前)读取本轮最新用户消息并分类,判定结果 缓存到当轮结束;agent/request 时应用到请求配置。中途转向(steer / 追加消息) 会触发重新判定。

判定规则(优先级从高到低)

  1. 显式标记:消息里带 [effort=off|high|max](也支持 【effort:…】、 {effort:…}、effort=…;low→off,medium→high)→ 直接采用
  2. 复杂任务关键词(maxKeywords:重构/架构/分析/refactor/design/debug…)→ max
  3. 继续类指令(continuationKeywords:继续/接着/next/continue…)→ 沿用上一轮
  4. 闲聊(offKeywords,先剥离 politenessPrefixes 如“好的/收到”)→ off
  5. 长指令(≥ longThreshold 字符)→ max
  6. 过短无信号(≤ shortThreshold 字符)→ 沿用上一轮
  7. 默认(defaultEffort)→ high

额外机制:

  • 轮内出错自动升级(escalateOnError):本轮工具调用报错后,剩余步骤强制 max
  • 子代理(subagents: "auto"):子代理按自己的提示词(委托指令)判定, 通常较长 → max;可设 "off" 完全不干预
  • 能力收敛:只会把 effort 设置到目标 provider+model 实际支持的档位 (查 ctx.llm.resolveModelInfo 并缓存),不会把 max 强加给不支持推理的模型 (如 qwen 视觉子代理)
  • 变化通知(notify):effort 相对上一轮变化时,向模型注入一行 <system-reminder> 说明,便于观察与调试

安装

方式一:npm / GitHub 包(推荐)

dsh plugin --profile web add dsh-task-effort
# 或从 GitHub:dsh plugin --profile web add github:zhangzhenwen1/dsh-task-effort

安装后重启 dsh web。可通过 profile 的 cordis.patch.yml 覆盖配置。

方式二:本地 patch(开发用)

在 ~/.dsh/profiles/web/cordis.patch.yml 的 insert 列表追加:

    - id: task-effort
      name: 'file:///home/zhang/文档/DSH/plugins/task-effort/index.js'
      config:
        providers:
          - deepseek-official
        defaultEffort: high

保存后 user patch 层热更新;若未生效,重启 dsh web。

配置项

键默认说明
enabledtrue总开关
providers["deepseek-official"]只调整这些 provider 的请求
defaultEffort"high"无信号时的默认档位
maxKeywords见源码复杂任务关键词(命中→max)
offKeywords见源码闲聊关键词(命中→off)
politenessPrefixes见源码判定前剥离的礼貌前缀
continuationKeywords见源码继续类指令(沿用上一轮)
longThreshold200消息长度超过即 max
shortThreshold4短于此且无信号则沿用上一轮
escalateOnErrortrue轮内工具报错后升级到 max
costAwaretrue时段感知:高峰时段(北京时间工作日 09-12/14-18)价格更高,自动压档省钱
peakCap"high"高峰时段的 effort 上限(max 被压到该档;可设 "low"/"off",null 关闭限档)
periodOverridenull测试用:强制时段 "peak" / "offpeak"(演示限档效果)
subagents"auto"子代理策略:auto / off
notifytrueeffort 变化时注入说明(含时段与距下一时段倒计时)
logtrue打印判定日志(task-effort: agent=… effort=… reason=…)

手动控制

  • GUI 模型选择器:你在界面里手动选过档位后,插件检测到选择偏离会自动尊重手动选择并暂停自动判定(界面显示的档位 = 实际请求档位,完全一致)。
  • 恢复自动模式:手动选择记录在运行进程内(Web 的 selectModel 状态),新建会话或重启 dsh web 后自动恢复。注:DeepSeek 模型有默认档位(如 high),所以选择器菜单里没有 "Provider default" 选项。
  • 单条消息指定档位:[effort=off]、[effort=max] 等(优先级最高,仅当轮生效;手动模式下同样生效)
  • 临时关闭:把配置里 enabled 改为 false,或移除 patch 条目

界面可见性

  • 每次 effort 切换,会话里会注入一行 <system-reminder> 说明(判定原因 + 档位 + 当前时段 + 距下一时段倒计时)
  • 插件应用档位后会自动通知界面刷新(llm/adapters-updated → 模型选择器重新拉取), 输入框旁的模型胶囊会显示实际生效的档位(Off / Low / High / Max)
  • 会话轨迹(request/header 事件)记录每次实际档位变化

已知限制

  • 判定是启发式的,误判时用 [effort=…] 标记兜底,并欢迎调整关键词表。