DeepSeek Harness Plugin Hub

发布与管理完整 Harness Profiles,发现适合你的插件。

探索

插件目录环境预设文档中心动态

社区

发布插件联系我们报告问题

相关链接

Plugin Hub GitHubDeepSeek Harness 官方项目系统状态隐私说明
© 2026 DeepSeek Harness Plugin HubPowered byPaxTech

独立、非官方社区项目,与 DeepSeek 官方无隶属、授权或背书关系。

Task Dispatch Table — DeepSeek Harness 插件(DSH Plugin)
DeepSeek Harness Plugin Hub
ProfilesPlugins分类动态文档登录管理 Profiles
ProfilesPlugins分类动态文档登录
← Plugins

dsh-task-dispatch-table

Task Dispatch Table

定时任务调度器:一个 dsh 主机插件,通过单个任务表驱动周期性代理任务,并将每次运行作为独立的 dsh 会话进行调度(调度本身不调用模型)

插件会安装到这里;不确定时保持 web。

npx -y @deepseek-ai/dsh plugin --profile web add dsh-task-dispatch-table@0.1.11
README兼容性版本
Task list with a task expandedThe task editor as a right-hand split panelRecurring schedule: daily at 18:12 with an allowed delayUpstream tasks declared in the editorA task expanded: runs table with status, times, token usage and artifactsThe archived session: files received from upstream tasks, task attachments, the dispatch request and token usageThe cross-task execution timeline, one entry expandedMonthly calendar with actual runs as filled dots and planned runs as dashed dots

兼容性与来源证明

Task Dispatch Table 以 dsh-task-dispatch-table 发布,当前版本为 0.1.11。Plugin Hub 会校验它的 manifest,并保存精确安装来源,便于复现安装结果。

DSH 兼容范围
*
运行环境
web
发布来源
npm
Registry 更新时间
2026/10/13

版本

0.1.11stable
2026/10/13
0.1.9stable
2026/10/12
0.1.6stable
2026/10/12
查看其余 3 个版本收起版本
0.1.4stable
2026/10/10
0.1.2stable
2026/10/9
0.1.1stable
2026/10/8

相关插件

正在加载相关插件…

最新版
0.1.11
DSH
*
HMR
重启进程
Tree shaking
未声明可安全裁剪
解包体积
8.2 MB
文件数
48
Surface
web
许可证
MIT
发布源
npm
GitHub
★ 2
周下载
0
最近提交
2026/10/15
查看源码 ↗
README Badge

点击下方 Badge 复制 Markdown,粘贴到 README 即可。

这是你的 Plugin?认领权益 · 优先安全扫描

验证 package.json 声明的 GitHub 仓库,即可管理这个公开页面。认领后,Hub 会优先安排当前版本的安全扫描,并在通过后公开展示结果。

认领这个 Plugin →
报告问题

相关插件

继续浏览 agents-orchestration 分类下经过校验的插件。

Headless@deepseek-ai/dsh-headlessdsh one-shot bundle:基于 dsh-base 的直接核心 Agent/Session 运行器,不包含 Host、HTTP 或浏览器层Experimental Agent Team Profile@deepseek-ai/dsh-experimental-agent-team-profile在一个实验性捆绑包中提供 Agent Teams 协作、工具和 Web UIExperimental Ralph Bundle@deepseek-ai/dsh-experimental-ralph-bundle使用全新代理执行明确请求的重复工作。Hindsight Coding Agents@vectorize-io/hindsight-coding-agents面向编程代理的仅反思式 Hindsight 长期记忆(可插拔支持多种运行框架:opencode、……),自动在后台导入(无需设置 CLI)。

README

dsh-task-dispatch-table · Scheduled task dispatcher

English | 中文

One dsh host plugin: a single table of task definitions drives your recurring agent work — when a task is due, it is dispatched as an independent dsh session that an agent actually executes. The scheduling itself is pure program logic and never burns a token.

Task list with a task expanded

  • Zero model involvement in scheduling — tick → check the schedule window → check dependencies → dispatch. Judgment-heavy work goes to the agent session; deciding when to run costs nothing
  • Three schedule modes — one-off, cron-style daily/weekly, or every-N-hours intervals, each with an allowed-delay window so a busy host catches up instead of silently skipping
  • Dependencies declared by the downstream — a task can require upstream tasks to have succeeded; the exact upstream instance and its outputs are frozen at dispatch time and handed to the downstream session
  • Every run is an independent session with its own status, token usage, artifacts and event log — inspectable afterwards, retryable on failure, serialized per task
  • A full UI — task list, per-task runs and logs, a cross-task execution timeline, a monthly calendar of planned and actual runs, a split-panel editor, and a settings page

Install

dsh plugin --profile web add dsh-task-dispatch-table

Every release is published to npm, so it works right after installing — no extra configuration and no local build. The UI copy is bilingual and follows dsh's interface language (Settings → General → Language).

How it works

The plugin keeps two layers of state:

ObjectWhat it isWhat it decides
Task definitionOne row per scheduled unit: title, prompt, schedule, attachments, workspace, model, dependencies, on/off switchWhether and how a task should run
Task instanceOne row per actual run: status, planned/actual time, session id, token usage, artifactsWhat happened in a run

The scheduler is a plain loop: on every tick it computes which tasks are due, claims them atomically in SQLite, dispatches each as a new dsh session in the task's workspace, then tracks the session via a receipt tool the session is required to call when done. Missed slots (host was down past the allowed delay) are recorded and marked skipped instead of disappearing.

Tasks

Creating and editing

The task editor as a right-hand split panel

Press New task (or Edit on a card) and the editor opens as a layout split panel, not a floating drawer: basics, schedule, prompt (with version history), advanced options, attachments and upstream tasks. Attachments are either links to files already in the workspace or uploads (stored in the task's own directory, up to 20 MB each).

The footer switches between View / Edit modes: View is a read-only rendering of the task — configuration, last run, and the prompt — for checking a task without risking an accidental edit.

Schedules

Recurring schedule: daily at 18:12 with an allowed delay

Three modes, each showing a plain-language preview of the next run:

  • Once — runs at the given moment, then never again
  • Recurring — daily / weekly / monthly at a given time
  • Interval — every N hours (or days), optionally restricted to selected weekdays

Every mode has an allowed delay: if the host was busy or down when the moment came, the run still fires within the window; past the window the slot is recorded as skipped (with the reason) rather than lost silently. A task card's Run now button triggers an extra run immediately, outside the schedule.

Dependencies

Upstream tasks declared in the editor

A task declares which upstream tasks must have succeeded before it may run (the Airflow / GitHub Actions needs model — the downstream declares, so adding a downstream never touches the upstream). When the task fires, the plugin freezes which upstream instance it matched together with that instance's outputs and passes them into the new session, so the downstream agent reads exactly the data its run was keyed to — even if the upstream has re-run since.

Runs and records

Per task

A task expanded: runs table with status, times, token usage and artifacts

Expanding a task opens three panels: basic info (configuration side by side with the last run), runs (one row per instance: status, planned vs actual time, duration, token usage, artifacts, and a button to open the archived session), and logs (the plugin's own diagnostic log for that task — missed slots, missing attachments, manual runs).

Session view

The archived session: files received from upstream tasks, task attachments, the dispatch request and token usage

View session opens the archived run as a read-only record: the files the session received from upstream tasks (frozen at dispatch time), the task's attachments, the dispatch request with its timing and token usage — and a continue conversation button that forks the archived session into a new interactive one.

Execution timeline

The cross-task execution timeline, one entry expanded

The Records tab is the ledger across all tasks, grouped by day and filtered by time range, workspace, status and task. Each entry expands in place to its full artifact list and raw event log (state changes, dispatch record, receipt); the archived session itself opens only when you press View session.

Calendar

Monthly calendar with actual runs as filled dots and planned runs as dashed dots

The Schedule tab is a month view. Days show two kinds of markers: actual runs from the instance table (solid dots in status colors) and planned runs computed from the current task definitions (dashed dots). Clicking a day expands that week in place with the full run details — the same entry blocks as the timeline, expandable again down to artifacts and events.

Configuration

Settings page: plugin settings on top, plugin log below

The Settings tab is the primary place to configure the plugin. Each item shows whether it was customized and can be reset individually; changes are staged and written only on Save; the log block below shows the plugin's diagnostic log with level coloring and auto-refresh.

ItemDefaultMeaning
Tick interval60 sHow often the scheduler scans the task table
Run log retention30 daysHow long diagnostic log rows are kept
Temp attachment retention7 daysHow long uploaded temp files are kept
Default modelfollow hostModel used when a task does not pick one
Dispatch grace60 sMax wait for a dispatched session to appear
Run lease1800 sHow long a silent session keeps its lease before being reclaimed
Observation window300 sHow long an unknown-status session is watched before being judged dead

Configuration is stored in the plugin's own state database, so it survives host config resets; defaults apply underneath.

Development

npm install
npm run build        # builds host first, then client
npm run typecheck
npm run smoke        # smoke tests against dist/

dist/ is a build artefact committed to git — dsh installs plugins from git/npm without running build scripts, so after changing src/ you must run npm run build and commit dist/ with it, or the change will not take effect.

License

MIT © 2026 cq-guojia