Плагины

Adds download buttons to the document preview toolbar and the Files tree, packs a folder download into a streamed ZIP, and adds a Files-tree upload button that streams to the Host one file at a time, capped at 1 GiB and renamed with an (n) suffix instead of overwriting.

Per-project MCP servers: a project declares servers in its own documents (`.dsh/mcp.json` by default; the local and global file lists are settings), and they are mounted only for the sessions working in that project — on the first turn of a session, released when it goes idle. A right-sidebar tab and a Settings page list each project with a live session, the status of every server and the session holding each mount, with `Sync` / `Retry` / `Release`, an `enabled` switch and an editor over one existing entry; a per-project tool policy (`disclosure` / `direct` / `off`) with pins and `mcp_search_tools` decides what the model sees; `${VAR}` references resolve through the project `.env` files and the credentials file; per-server call counters outlive the sessions that produced them.

Document intake for agents: doc_route sniffs a file's real format by magic bytes and measures a PDF's text layer and page column layout before any conversion, and pdf_markdown converts PDFs to Markdown in column reading order with PyMuPDF. The PDF path needs a Python 3 interpreter with PyMuPDF.

Adds a human-editable notes workspace with folders, full-text search, rich text, checklists, resizable tables, attachments, exports, and opt-in agent collaboration.

DSH plugin: only ping me when the agent has really finished AND I have not come back for N minutes. Configurable dwell, brief result summary, plain SMTP or a local outbox.

Replaces the sidebar workspace region with a two-tab browser: several workspace roots stay registered side by side while conversations are filed under the real working directory of each session, with a read-only resource tree that previews files in the right sidebar. Hiding is per tab, display-only and fully reversible; a resource folder or file can be copied as a path or dragged into the composer as a native reference, and @ completion covers every registered root rather than the working directory alone.

Deterministic, zero-LLM, byte-budget context compaction for DeepSeek Harness, with byte-exact recall of compacted history.

Honest merge of two community plugins into one calmer display: the streaming reading view from dsh-better-display (fork) and the message rail from dsh-tidychat. For theme lovers it wraps reasoning prose and tool-call output in translucent message bubbles, so text no longer sits directly on busy wallpapers or skins where it is hard to read. Cross-version rc adaptation attempted across DSH 0.1.0-0.2.0 (all rc); no obvious problems so far.

Session management for DSH: archive/restore, batch & conditional delete, AI auto-rename, interrupted-session auto-resume, workspace grouping, undo last message, repair damaged session logs (seq-gap/EIO/dual-format), value analysis and full-text search — plus plan/closing template injection (system prompt + context).

TRAE-style conversation rollback rebuilt for DSH 0.1.7-rc.2: per-turn file checkpoints restore touched files and truncate the model context in place under the same session id. Adds a /rollback doctor framework-contract self-check, an affected-file diff preview computed against the current on-disk state so it stays correct after a restart, a one-click undo-last action with a Ctrl+Shift+Z shortcut, a setting for whether rolled-back messages stay hidden, and English UI text.

Turns large text pastes into pastes/*.txt attachments with a dock above the composer and a minimal, recognisable badge in the draft.

One-tap connect Agnes language, image and video models into DSH (off by default), with image recognition and thinking level filled in automatically. After signing in to the Agnes console (re-login uses AGNES_PASSWORD), you can see the quota windows (5-hour requests, weekly requests, daily images, video), account-wide cumulative usage, and a usage pill beside the input box. AgnesCode desktop models can be connected too (Windows only), re-reading the desktop app login when the token expires, with rate-limit hits backing off on their own.

Personal coding assistant that schedules, follows up on and verifies local Codex or Claude Code tasks from DSH, with WeChat, WeCom and Feishu remote channels.

Google-AI-Studio-style turn controls for DeepSeek Harness, in one install: edit a prompt and re-run it, re-run a reply in place, delete a turn from the model context, and render sent prompts as Markdown. Self-contained: the plugin list shows this one row;

Terminal-style music video player for DeepSeek Harness Desktop: canvas MVs synced to your own audio file, MV packs (mv.json) for any song, sandboxed scene scripts and a GitHub-hosted workshop (创意工坊) — the world.execute(me) ASCII scenes and the dsh PV are

Read-only Skill inspector for DeepSeek Harness. It shows which Skills a conversation actually loaded — from observed loading evidence only — and which Skills the current environment can discover, and gives each Skill a detail page whose left column switches between the framework, the evidence, validation, evaluation, step evidence, run logic, the before/after of a modification when there is one, the definition facts and the raw SKILL.md. Declaration and run stay apart: the body is split into structure, declared workflow and progressive disclosure, the run logic is read from local receipts, and every declared step carries its own evidence — no observed evidence is reported as exactly that, not as executed or not executed, and the run's instruction hash sits beside the current definition as match, mismatch or unavailable. The evidence view gives each subject one of three states (declared, observed, unavailable), walks definition → load → use → outcome, names what each stage cannot reach, declines to attribute an outcome to the Skill, and can copy the snapshot out as byte-stable JSON. Validation checks the Agent Skills open standard and the platform profiles separately, each finding on a rule id and labelled standard compliance or platform compatibility. Evaluation keeps repeatable cases with the conditions each run was recorded under and the four stages of runtime evidence, comparing two runs of one case item by item without scoring them. The trigger boundary keeps should-trigger and should-not-trigger prompts, has you run them in a real new session, then records what was observed — whether a load record appeared and whether it was model-invoked or user-explicit; a typed /name is not a natural trigger, and an absent load record is reported as not observed, not as not triggered. The same projections are exposed to the agent as a read-only skill_review tool, which returns a structured review packet and says what it omitted when the packet will not fit whole. The inspector, the evidence chain and these reviews are computed on this machine from the definition and the session receipts; the Chinese reading version sends the body through the host's model when you ask for it, keeping code fences, paths and frontmatter verbatim and storing the result on this machine. A Skill can also be cloned into a local copy. It does not write back to the source Skill and does not run its scripts.

TinyFish-backed search and fetch providers for the DeepSeek Harness web capability seam (ctx.web) — $0 SERP and page extraction, direct or via Monid.

Image generation with a sidebar gallery page and three agent tools (paint_image, paint_images, edit_painting); preset providers include ModelScope, Google Gemini, OpenAI, SiliconFlow, Volcengine Seedream, Alibaba DashScope, xAI and Zhipu, plus any OpenAI-compatible endpoint, each with its own proxy setting.

Zero-token DuckDuckGo search provider for the DeepSeek Harness (DSH) web seam — local headless browser, no API key, no model billing

Keeps a project's documentation in step with its decisions on DeepSeek Harness: the same append-only decision log and derived design snapshot, kept fresh in-process instead of by a hook process.

Lets the model trigger compaction itself at a safe point via a compact_now tool (works mid-turn), plus a context_status tool reporting real token usage against the session's actual context window.

DeepSeek Harness plugin for Agent-Playbook: multi-agent claims, isolated git worktrees, and enforced acceptance checks. "Done" is an exit code, not a claim.

独立本地记忆插件：JSONL 记忆条目、每轮 runtime-context 注入、local_memory_search/local_memory_remember 工具、设置面板管理页。不依赖 Mnemon。

Readable transcript export for DeepSeek Harness: turn any Session into a Markdown / HTML / ZIP transcript with reasoning blocks, tool calls and results, images and usage — from the Session header or the /export-md command.