Workflow & Automation

Host-side scheduled jobs on cron, RRULE or one-time schedules: shell commands that start no model, gated jobs that wake an agent only when the command reports work, or agent prompts. Agent tools to create jobs, a Cron tasks page, and result delivery through any plugin that exposes a send method.

DSH 上下文接力插件（Context Relay）：phase 协议 + 预算哨兵 + 受控压缩 + 有界 handoff 开新会话 + 队友保鲜（工作记录/体检/换代/链式召回），让 Lead 与队友长期停留在高效上下文区间。

Evidence-gated acceptance for research reports: claims, citations, data scope and method limits each need a tick plus written evidence before a deliverable can pass, with same-artifact revision history and a standalone SHA-256 receipt that says when the bytes moved.

A project lead for DeepSeek Harness. Opening a session with the dsh-master preset in a folder makes it that project's master: it splits your requests into tasks, dispatches them to member sessions over plugin-delivered messages, collects structured reports and stops at every gate for review. Members ask you only through the master, as clickable cards on a native side-panel board. A tagged devlog is pushed back into context before related files are touched. Guards keep agents off the plugin's state and git index, and a quiet patrol plus a safety-net schedule watch for stalls. One-click pause per project; all state stays local. Requires DSH 0.2.1 or 0.2.2, has only been tested on macOS, and the UI is Chinese-only.

Adds a clarify mode: the agent loses its file-writing tools and can only ask questions until the required dimensions are covered, then writes a spec with acceptance criteria before implementing.

Reusable workflows: orchestration scripts saved as files under .dsh/workflows, discovered from the project, and run by name with arguments, so they live in git and can be shared. Four tools: list, show, run, save.

Six-step video-replica workbench: fetches a Douyin/Xiaohongshu/WeChat Channels/Kuaishou/Bilibili share link or a local file, breaks the source into shots with a vision model and optional ASR, writes three A/B/C storyboards, generates a first frame and a clip per shot, then stitches the final video with optional TTS narration, burned-in ASS subtitles and BGM. Needs Node 22.18+/24.11+, ffmpeg and ffprobe on PATH, and configured vision/chat/image/video model endpoints; share links go through a third-party parser service (or yt-dlp), or upload a local file.

Evidence-gated teaching-material workbench with a Web UI: page model, per-page handout and slide editing, PAEG Chinese language checks, layered gates, checks center, version history, handout/deck/storyboard/Manim-script export and rights audit.

Restart DSH and find out whether it actually came back. Windows has no external way to make Electron quit cleanly (WM_CLOSE just minimises the window), so this plugin does not pretend: it terminates the host, relaunches it with retries, then polls the host port until it really serves again, and reports the outcome to a local result file plus a QQ message when qq-notify credentials (appId/clientSecret/openid) are configured in the desktop profile. Verified end to end on 2026-11-08.

DeepSeek-Harness 插件：轮次收尾时若模型未声明目标状态，注入续行提醒而非放行。处理思考泄露、工具调用畸形、上游断流导致的任务静默中断；上游中断类型可重试错误耗尽后自动续行，默认上限 3 次，跨进程共享计数。含设置界面与判定留痕

Local-first task workbench for DeepSeek Harness with today, week and all-task views, single-day and multi-day tasks with optional times, a four-state idea pool, and daily/weekly/monthly reviews that only a human can write.

AI-native iteration cycle: 24 anic_* tools and 77 HTTP routes that run evaluation, convergence gates, and auto-fix loops across projects, with a live white-box panel (interactive workflow graph, invocation feed, autonomy gauge, gate ledger, HITL queue) and an inline installable SKILL.md workflow kit.

Long-form manuscript verification team for DSH: installs 10 skills that run a read-only content/structure check, three-tier revision proposals, a human-selection gate, exact replacements and a final re-check; it never edits the manuscript by itself and requires Agent Teams to spawn teammates.

Turns your local WeChat group chats into a followable todo board: a three-column kanban (todo / doing / needs you) with LLM summaries, automatic flagging of messages that @-mention or reply to you, drag-to-change status, and local-only storage. Needs a local Python 3 with sqlcipher3 and zstandard, plus the existing rion-wechat-reader config.json and keys.json for the WeChat databases; the plugin does not extract the keys itself, and summaries send the quoted chat text to the model you choose.

Discourages unnecessary sequential tool calls by guiding the model to batch ready, independent calls, potentially reducing wait time, model round trips, and token use when the runtime supports parallel execution; no scheduler changes.

Agent preset that hands every task to a Claude Code subagent, so the session only writes the task brief, delegates and reports the result. Requires a locally installed, logged-in Claude Code.

Tells the parent agent when a subagent died from an upstream failure instead of finishing: it listens to agent/error on every agent, waits a short settle delay, and if the child is still not running delivers a followup turn to the parent carrying the child id, the failure and the options the parent has, with a cooldown and a per-child cap so a flapping provider cannot flood the parent.

Right-sidebar flow editor for prompts, model switches, commands, condition branches and loops, executed only at turn boundaries so an in-flight request keeps its model.

A fact layer for daily heartbeat turns: diffs the curated plugin market for newly published entries and the Chinese education SRC calendars (EDUSRC rounds, Beijing education SRC seasons, the standing vulnerability-hunting exercise) for new items. Reports deltas only — the first call seeds a baseline and stays quiet.

Scheduled model-news radar: collects official release announcements from LLM vendors through RSS, Hugging Face and GitHub organisation APIs and changelog pages (a 6-vendor sample list is bundled, a user-maintained list is read from ~/.dsh/model-news-radar/sources.json), deduplicates them into daily, weekly or monthly Markdown reports and opens a DSH session that writes the summary. Read-only, no logins, no third-party dependencies.

DeepSeek Harness plugin: Aliyun Yunxiao requirements and defects kanban by status, with detail drawer, image preview, one-click session dispatch, Req/Bug creation, and native tools for status transitions, work item creation, project member lookup, change-

Incrementally sync Tsinghua Learn course materials through a companion browser extension, with local file checks and per-run logs.

Personal todo list as a right-Sidebar tab: categories, groups, five states, backup and export, stored per session.

Task list panel docked to the left of the conversation column: five states, parent/child folding, abandoned and completed docks, shared with the agent through task_list / task_write.