Plugins

Markdown-authoritative second brain: layered memory, local recall, and a daily Bilibili feed that writes source pages and recent notes back to Obsidian.

Workspace artifact manager that sorts files into artifact, process, memory and material roles, with extra workspace roots, 12 file types, a year/month/day timeline, preview, rename, trash, zip archive and optional COS sync.

Caps how many DeepSeek Harness conversations run at once, so extra conversations wait in a FIFO queue instead of piling up model requests. On Windows a bottom status strip shows physical memory, commit memory and disk usage; on other platforms only the queue and physical memory are reported. A plugins-page card changes the limit.

Deletes a whole workspace together with its conversations in one pass - session logs, projection caches and workspace registrations - and optionally sends the workspace folder to the Windows Recycle Bin (on other platforms deletions are permanent).

Auto-titles conversations after the first user+assistant exchange, with a chat header button to update or manually edit titles.

Layered context management: at each turn end older tool output becomes a deterministic card, the model can fold older ranges into its own summaries in up to three tiers (compress), and every original is archived locally for decompress and search_context. Works alongside DSH-Mem0: superseded runtime-context snapshots (such as recalled memories) are never archived, carded or folded, and are replaced by a one-line placeholder at turn end when the prompt cache is already broken, when the saving outweighs the cache miss, or above 75% of the window; a strataBudget service (pressure, allowance, countTokens) and a strata/fold-landed event are provided for other context plugins; strata_status warns when DSH's automatic compaction is off or its official summary keeps failing. Its L1 layer, archive rotation, prune guard and preset takeover are forked from dsh-live-compact 1.0.6 (MIT); uninstall dsh-live-compact or billion-context first — they replace the same compaction rows and Strata will not take over while either is installed.

Shows OpenCode Go usage (5-hour, weekly, monthly) in the DSH composer dock and a Settings page.

Sidebar hub for the WorkBuddy, Trae and Qoder connect plugins: one-click or per-platform daily check-in across every pooled account, per-account credit balance with today's state and expiry, a credit-package breakdown, account add/remove (WorkBuddy OAuth, Qoder PAT), and one-click joining the pool for an account that is signed in but not yet enrolled. It stores no credential and calls no platform API itself.

Manage native themes and installed theme plugins from a right-sidebar panel and a Settings page, with only one theme active at a time. Listing and toggling installed theme plugins requires dshmarket; the right-sidebar tab requires dsh-better-sidebar (otherwise the panel appears only in Settings).

Gives each Workspace a stable tint from a warm-to-cool ramp, sets its name as a section heading above indented Sessions, and turns a finished unread chat's row green.

Adds a pin button to the left of the Windows caption buttons that keeps the DSH window always on top of the desktop.

Keep your git workflow inside DeepSeek Harness. A composer chip shows the current branch at a glance; the TRAE-style popup lets you switch or create branches, fetch remotes, commit & push a subset of changes, merge with a clear source -> target flow, and stash / restore partial changes — all without leaving the chat. Popovers dock above the composer so your draft stays visible; the change list is prefetched when the menu opens; and the plugin confirms before touching a dirty tree.

输入框下的会话级用量计费胶囊：官方峰谷价目、剩余余额、Tokens 与成本

Fail-closed retry protection and evidence-backed recovery for DeepSeek Harness (DSH) tools.

Groups sidebar conversations into collapsible folders that reorder by drag, decorating the shipped session list instead of replacing it.

LAN access for the harness process: writes the authenticated links for the harness port, one per local IPv4 address, to a token file and registers DSH_LAN_LINK in the shell environment, and can run a gateway on a fixed LAN port that holds the browser session on this machine, so devices need no token; forwarded requests get Host and Origin rewritten for the same-origin guard, and a host-claim marker is injected so the page renders as the full desktop UI instead of remote-visitor mode. Devices are admitted by CIDR, with optional Basic auth.

Backs up and restores the whole DSH profile through a private Git repository: profile configuration, per-plugin settings, skills, installed plugins and MCP servers, with one-click backup and restore and a restore point written before anything is overwritten.

Approval reminder: an in-page card with Allow once / Reject when a session waits for permission, plus optional desktop notification, sound and phone push through PushPlus, ServerChan, ntfy, WeCom or a custom webhook.

MiniCut tools for making multi-shot AI short films through the MiniCut CLI: status, next step, and run, with a price shown and the user's yes required before any paid job.

Windows-only sidebar panel that watches the CPU and IO of your AI desktop apps' process trees and shuts the machine down once all of them have been idle for a configurable time, with a cancellable countdown, a dry-run mode and an activity log; requires Python 3.10+.

Local-first resume warehouse for DeepSeek Harness: package your work into reusable bullets, import an existing resume into a template, analyse a job description (including the school-tier preference it implies), assemble a tailored Chinese or English resume and export a PDF named position-name-school. The whole app ships inside the npm package — server/, web/, skills/, scripts/, requirements.txt, no git clone needed — and one tool starts, stops and health-checks it; the first start installs the dependencies into app/.venv. Needs Python 3.10+ and macOS or Linux (bash). Nothing leaves the machine except the LLM calls you confirm.

Per-workspace personal knowledge base for DeepSeek Harness: each identity gets an isolated local library — import PDF, Word, Excel, Markdown, text, HTML and images, auto-chunk and embed into SQLite with FTS5 + vector hybrid retrieval, then ask questions in chat with numbered citations back to the source. Local-first, no cloud upload; vector embeddings need a local Ollama (default bge-m3), and without it retrieval degrades to FTS5 keyword search.

Injects your own text into the DeepSeek Harness system prompt as real system sections from a sidebar editor: each section lands after the persona, after the tool docs, or at the very end of the prompt, can be switched on or off, and can resolve {{variables}}; a preview runs the host's own assemble and render pass so you see the exact prompt the next request will send, with empty, duplicate, unknown-variable and oversize sections flagged.

Signs in to ima.qq.com (Tencent IMA) with a WeChat QR code and runs a localhost OpenAI-compatible relay in front of its SSE chat endpoint, so the four models behind it appear in the picker.